Publications

@article{author2026evaluating,
  author = {Author, A. and Author, A. and Blake, John and Authors, More},
  title = {Evaluating Native and Foreign Language Practice with an Embodied Virtual Agent through Biosignal Analysis},
  year = {2026}
}

Author, A., Author, A., Blake, J., & Authors, M. (2026). Evaluating Native and Foreign Language Practice with an Embodied Virtual Agent through Biosignal Analysis. .

The increasing volume of digital linguistic evidence and the expansion of virtual communicative spaces demand forensic linguistic tools that are both methodologically rigorous and accessible to a wider range of users, including legal practitioners. This paper introduces a bespoke, web-based authorship analysis tool designed to identify and visualize key textual patterns across questioned and known datasets. Operating through an intuitive graphical user interface, the tool offers an accessible alternative to command-line methods, expanding the reach of computational forensic linguistics to non-technical users. The tool integrates two core functionalities: (1) automated identification and comparison of shared n-grams, particularly bigrams and trigrams, within and between datasets, and (2) Key Word in Context (KWIC) exploration to support the interpretation of overlapping or distinctive lexical patterns. By combining these capabilities, the system enables both confirmatory and exploratory analysis of linguistic evidence, supporting investigations where authorship is contested or where stylistic consistency must be assessed. It has applications across the three domains of forensic linguistics: language as evidence, interaction in legal settings, and language of the law. In addition to its methodological contributions, the paper addresses key challenges in forensic semiotics: subjectivity, reproducibility, and transparency. It shows how computational approaches can mitigate the "subjectivity effect" by offering replicable, data-driven analyses of linguistic behaviour. Courtroom admissibility is also supported by producing clear, step-by-step analytical records and exportable logs that document each analytic operation. Our contribution aligns with the aims of computational forensic linguistics to enhance the interpretive rigour and evidentiary validity of linguistic analyses.

@article{blake2026bridging,
  author = {Blake, John and Kredens, Krzysztof},
  title = {Bridging Accessibility and Rigour: A Web App for Authorship Analysis Incorporating KWIC Exploration and Shared N-gram Profiling},
  year = {2026},
  journal = {International Journal of Semiotics and Law}
}

Blake, J., & Kredens, K. (2026). Bridging Accessibility and Rigour: A Web App for Authorship Analysis Incorporating KWIC Exploration and Shared N-gram Profiling. International Journal of Semiotics and Law.

@article{author2026an,
  author = {Author, An and Blake, John and Author, Another},
  title = {An Extensible Framework for Interactive Pronunciation Support for Orthographically Complex Languages: The Case of Sinhala},
  year = {2026},
  journal = {journal}
}

Author, A., Blake, J., & Author, A. (2026). An Extensible Framework for Interactive Pronunciation Support for Orthographically Complex Languages: The Case of Sinhala. journal.

@article{blake2026a,
  author = {Blake, John and Author, An},
  title = {A rule-based algorithm for identifying request head acts in L2 English learner emails},
  year = {2026}
}

Blake, J., & Author, A. (2026). A rule-based algorithm for identifying request head acts in L2 English learner emails. undefined.

Automated writing evaluation can be effective in providing support for L2 English learners. However, little research to date has investigated its use in the teaching of pragmatics in relation to L2 email writing, grounded in a sociocultural perspective on learning. We employ a quasi-experimental approach, investigating the effectiveness of a computerised dynamic assessment programme (C-DA) of L2 email writing, focusing on pragmatic development. The C-DA employs a developmentally sensitive approach, providing automated, immediate mediation to learners. The C-DA was administered twice – with a two-week delay between administrations – to a single group of 17 Japanese English L2 learner participants at a Japanese university; participants were 19–22 years of age with intermediate L2 proficiency levels. Text, identified pragmatic failure and mediation data were elicited from both administrations. Analysis of pragmatic failure frequency and explicitness of the mediation necessary for successful resolution of the identified pragmatic failure shows both frequency and explicitness decreasing not only within a round of administration, but also between rounds. Evidence of learner development was found across all types of pragmatic failure, including the requesting head act, email openings and closings. The study provides evidence to support a sociocultural approach to assessment and learning with regards to the pragmatics aspect of L2 email writing, in which mediation is sensitive to individual learners’ developmental needs. Further, findings support the use of a computerised approach to DA focusing on pragmatic competence, allowing for wider access to DA methodology among large learner group contexts.

@article{nicholas2026evaluating,
  author = {Nicholas, A. and Blake, John and Perkins, J. and Mozgovoy, M.},
  title = {Evaluating the effectiveness of a computerised dynamic assessment of L2 English email requests},
  year = {2026},
  journal = {Computer Assisted Language Learning},
  volume = {39},
  number = {1-2},
  pages = {303--335},
  doi = {10.1080/09588221.2024.2374775}
}

Nicholas, A., Blake, J., Perkins, J., & Mozgovoy, M. (2026). Evaluating the effectiveness of a computerised dynamic assessment of L2 English email requests. Computer Assisted Language Learning, 39(1-2), 303–335. https://doi.org/10.1080/09588221.2024.2374775

This study investigates the use of a pragmatics-focused computerized dynamic assessment (C-DA) of request-based L2 English email writing among Japanese university learners of English. The C-DA administers four email tasks to learners, automatically identifies perceived instances of pragmatic inappropriateness in texts and provides feedback, based on learner corpus perception data. The study compares the C-DA’s effectiveness in promoting learning among three participant groups: a graduated feedback group received feedback based on the concept of the zone of proximal development (ZPD); an explicit-only group received explicit feedback, and a control group did not receive feedback. The C-DA was administered twice, with a two-week delay between administrations. Both treatment groups showed evidence of development to a greater extent than the control both within a session and between sessions in terms of openings, closings and modification strategies. Comparing treatment groups, the graduated group responded more to feedback within a session for openings and closings, but not for modification strategies. Between sessions, there was no difference between treatment groups; however, across the entirety of the study, the graduated feedback group responded significantly more to feedback. Findings provide support for computerized approaches to L2 email writing feedback, and for approaches sensitive to a learner’s ZPD.

@article{nicholas2026impact,
  author = {Nicholas, A. and Blake, John and Perkins, J. and Mozgovoy, M.},
  title = {Impact of graduated versus explicit-only feedback in a computerized dynamic assessment of Japanese learners' L2 email writing},
  year = {2026},
  journal = {Applied Pragmatics},
  doi = {10.1075/ap.23018.nic}
}

Nicholas, A., Blake, J., Perkins, J., & Mozgovoy, M. (2026). Impact of graduated versus explicit-only feedback in a computerized dynamic assessment of Japanese learners' L2 email writing. Applied Pragmatics. https://doi.org/10.1075/ap.23018.nic

This paper presents a novel algorithm that leverages cutting-edge machine-learning techniques to accurately and efficiently detect AI-generated texts. Rapid advancements in natural language processing models have led to the generation of text closely resembling human language, making it increasingly difficult to differentiate between human and AI-generated content. However, misuse of such texts presents a serious and imminent threat to the quality of academic publishing. This underscores the urgent need for robust detection mechanisms to ensure information quality, maintain trust, and preserve the integrity of research publications. Our proposed model outperformed existing algorithms for accuracy with less computational complexity. The proposed model is a feature-based hybrid deep learning network that leverages part-of-speech tagging and integrates Bidirectional Long Short-Term Memory (Bi-LSTM) networks with Attention modules. The initial module extracts local contextual features using convolutional layers, followed by Bi-LSTM layers that capture long-term dependencies from past and future sequences. An attention mechanism highlights critical sequence components, enhancing the model’s focus on relevant data. The outputs from the attention and initial modules are concatenated through a residual connection, ensuring comprehensive feature representation. This combination is then fed into dense layers for final classification, effectively balancing feature richness and computational efficiency. The proposed model was evaluated on two benchmark datasets, achieving 85.00% and 88.00% accuracy, respectively.

@article{blake2025detection,
  author = {Blake, John and Miah, A.S.M. and Kredens, K. and Shin, J.},
  title = {Detection of AI-generated texts: A Bi-LSTM and attention-based approach},
  year = {2025},
  journal = {IEEE Access},
  volume = {13},
  pages = {71563--71576},
  doi = {10.1109/ACCESS.2025.3562750}
}

Blake, J., Miah, A., Kredens, K., & Shin, J. (2025). Detection of AI-generated texts: A Bi-LSTM and attention-based approach. IEEE Access, 13, 71563-71576. https://doi.org/10.1109/ACCESS.2025.3562750

This paper introduces the Feature Visualizer, an open-access AI-powered tool designed to raise genre awareness among novice academic writers through inductive learning, a process that includes approaches such as discovery learning. The tool houses an annotated corpus of scientific research articles written by computer science majors and allows learners to explore authentic texts using on-demand visualizations and multimodal explanations. By engaging with the corpus, learners identify recurring language patterns and rhetorical structures at macro, meso, and micro levels, facilitating the bottom-up discovery of genre conventions. A longitudinal study with Japanese undergraduate computer science majors showed that the tool enhanced learners’ awareness of academic writing conventions and genre features. Focus group interviews further confirmed the usability and pedagogical value of the Feature Visualizer. We conclude by discussing practical applications for genre-based writing instruction informed by inductive learning principles.

@article{blake2025raising,
  author = {Blake, John and Mozgovoy, M.},
  title = {Raising genre awareness though visualizing language features},
  year = {2025},
  journal = {Applied Corpus Linguistics},
  volume = {5},
  number = {3},
  pages = {100162},
  doi = {10.1016/j.acorp.2025.100162}
}

Blake, J., & Mozgovoy, M. (2025). Raising genre awareness though visualizing language features. Applied Corpus Linguistics, 5(3), 100162. https://doi.org/10.1016/j.acorp.2025.100162

This study investigates the potential for Large Language Models (LLMs) to scale-up Dynamic Assessment (DA). To facilitate such an investigation, we first developed DynaWrite—a modular, microservices-based grammatical tutoring application which supports multiple LLMs to generate dynamic feedback to learners of English. Initial testing of 21 LLMs, revealed GPT-4o and neural-chat to have the most potential to scale-up DA in the language learning classroom. Further testing of these two candidates found both models performed similarly in their ability to accurately identify grammatical errors in user sentences. However, GPT-4o consistently outperformed neural-chat in the quality of its DA by generating clear, consistent, and progressively explicit hints. Real-time responsiveness and system stability were also confirmed through detailed performance testing, with GPT-4o exhibiting sufficient speed and stability. This study shows that LLMs can be used to scale-up dynamic assessment and thus enable dynamic assessment to be delivered to larger groups than possible in traditional teacher-learner settings.

@article{jaganov2025large,
  author = {Jaganov, T. and Blake, John and Villegas, J. and Carr, N.},
  title = {Large Language Model-Driven Dynamic Assessment of Grammatical Accuracy in English Language Learner Writing},
  year = {2025},
  journal = {IEEE Access},
  volume = {13},
  pages = {151538--151550},
  doi = {10.1109/ACCESS.2025.3603191}
}

Jaganov, T., Blake, J., Villegas, J., & Carr, N. (2025). Large Language Model-Driven Dynamic Assessment of Grammatical Accuracy in English Language Learner Writing. IEEE Access, 13, 151538-151550. https://doi.org/10.1109/ACCESS.2025.3603191

Using the linguistic methods of metaphor, discourse, and comparative analysis, this study presents the problem of authentic translation of the composition titles from Tchaikovsky’s Children’s Album, Op. 39, for English editions or concert programs. We examine this problem from the perspective of the origins of this piano masterpiece and its subsequent transformations. Among many other factors, reordering of the compositions influenced the editorial decisions on selecting the proper equivalents for titles in English. Specifically, we explore how appropriate translations of the composition titles can help in preserving the important historical and cultural connotations and musical authenticity of the 24 piano pieces known as the Children’s Album, and therefore contribute to a better understanding of the whole original masterpiece, particularly in light of the significant reordering of the pieces in the first published edition compared to the original manuscript. By comparing the number of canonical known editions, we suggest a model designed to address the evident “lost in translation” issues in existing editions and resources.

@article{pyshkin2025lost,
  author = {Pyshkin, E. and Blake, John},
  title = {"Lost in Translation"? Challenges in Conveying the Original Titles of Tchaikovsky's Children's Album},
  year = {2025},
  journal = {Terra Linguistica},
  volume = {16},
  number = {1},
  pages = {99--111},
  doi = {10.18721/JHSS.16107}
}

Pyshkin, E., & Blake, J. (2025). "Lost in Translation"? Challenges in Conveying the Original Titles of Tchaikovsky's Children's Album. Terra Linguistica, 16(1), 99-111. https://doi.org/10.18721/JHSS.16107

This research contributes to the studies on the origins and transformations of Tchaikovsky's Children's Album, Op. 39 using the linguistic methods of discourse, metaphor, and comparative analysis to explore a number of connected questions and their impact on how the audiences and scholars perceive and understand the compositions. These methods are supported by the technology provided by computational linguistics, such as large language models along with music analysis algorithms based on signature pattern elicitation. This article examines how artificial intelligence technologies can shed light on the differing views on the Children's Album. The meanings and implications of the published reordering of the pieces are explored. The influence of Schumann's Album for the Young and the broader pedagogical and cultural significance of editorial transformations is investigated. Through this interdisciplinary approach, this study offers new insights into the compositional intent and interpretive possibilities of Tchaikovsky's work. The presented results of the musicology, literary, computational, and linguistic analyses complement the few scholarly studies aimed at unveiling the intriguing metaphors and connections of the Children's Album, which tend to remain in the shadows of his larger-scale piano and symphonic works.

@article{pyshkin2025restoring,
  author = {Pyshkin, E. and Blake, John},
  title = {Restoring Authenticity: Literary, Linguistic, and Computational Study of the Manuscripts of Tchaikovsky's Children's Album},
  year = {2025},
  journal = {Arts},
  volume = {14},
  doi = {10.3390/arts14030049}
}

Pyshkin, E., & Blake, J. (2025). Restoring Authenticity: Literary, Linguistic, and Computational Study of the Manuscripts of Tchaikovsky's Children's Album. Arts, 14. https://doi.org/10.3390/arts14030049

Teaching philosophy statements are often declarations of beliefs interspersed with descriptions and metaphors. The disjuncture between the stated philosophy and actual teaching has been raised by numerous academics. This case study addresses the neglected area of grounding teaching philosophies on actual teacher behaviour rather than on espoused beliefs. This study includes a replicable framework for teachers to create evidence-based teaching philosophy statements through a systematic investigation of their actual teaching practices. A retrospective think-aloud protocol was used to recount a lesson. Using a transcript of the recount, the teacher's actions were identified, extracted, and justified following pre-determined protocols. References to theoretical and empirical studies supporting or contradicting the justifications were checked in the research literature. To counteract potential self-bias, colleagues' views on the reasons selected were surveyed. The discrepancy between the teacher's justification of actions and the peers' perspectives revealed hitherto hidden idiosyncrasies and underlying values.

@article{blake2024aligning,
  author = {Blake, John},
  title = {Aligning teaching philosophy statements with practice: An evidence-based approach using retrospective think-aloud protocols},
  year = {2024},
  journal = {Education Sciences},
  volume = {14},
  number = {7},
  pages = {795},
  doi = {10.3390/educsci14070795}
}

Blake, J. (2024). Aligning teaching philosophy statements with practice: An evidence-based approach using retrospective think-aloud protocols. Education Sciences, 14(7), 795. https://doi.org/10.3390/educsci14070795

This paper discusses the challenges posed in creating a Computer-Assisted Pronunciation Training (CAPT) environment for multiple languages. By selecting one language from each of three different language families, we show that a single environment may be tailored to cater for different target languages. We detail the challenges faced during the development of a multimodal CAPT environment comprising a toolkit that manages mobile applications using speech signal processing, visualization, and estimation algorithms. Since the applied underlying mathematical and phonological models, as well as the feedback production algorithms, are based on sound signal processing and modeling rather than on particular languages, the system is language-agnostic and serves as an open toolkit for developing phrasal intonation training exercises for an open selection of languages. However, it was necessary to tailor the CAPT environment to the language-specific particularities in the multilingual setups, especially the additional requirements for adequate and consistent speech evaluation and feedback production. In our work, we describe our response to the challenges in visualizing and segmenting recorded pitch signals and modeling the language melody and rhythm necessary for such a multilingual adaptation, particularly for tonal syllable-timed and mora-timed languages.

@article{blake2024an,
  author = {Blake, John and Bogach, N. and Kusakari, A. and Lezhenin, I. and Khaustova, V. and Xuan, S.L. and Nguyen, V.N. and Pham, N.B. and Svechnikov, R. and Ostapchuk, A. and Efimov, D. and Pyshkin, E.},
  title = {An Open CAPT System for Prosody Practice: Practical Steps Towards Multilingual Setup},
  year = {2024},
  journal = {Languages},
  volume = {9},
  number = {1},
  pages = {27},
  doi = {10.3390/languages9010027}
}

Blake, J., Bogach, N., Kusakari, A., Lezhenin, I., Khaustova, V., Xuan, S., Nguyen, V., Pham, N., Svechnikov, R., Ostapchuk, A., Efimov, D., & Pyshkin, E. (2024). An Open CAPT System for Prosody Practice: Practical Steps Towards Multilingual Setup. Languages, 9(1), 27. https://doi.org/10.3390/languages9010027

Skin cancer poses a significant healthcare challenge, requiring precise and prompt diagnosis for effective treatment. While recent advances in deep learning have dramatically improved medical image analysis, including skin cancer classification, ensemble methods offer a pathway for further enhancing diagnostic accuracy. This study introduces a cutting-edge approach employing the Max Voting Ensemble Technique for robust skin cancer classification on ISIC 2018: Task 1-2 dataset. We incorporate a range of cutting-edge, pre-trained deep neural networks, including MobileNetV2, AlexNet, VGG16, ResNet50, DenseNet201, DenseNet121, InceptionV3, ResNet50V2, InceptionResNetV2, and Xception. These models have been extensively trained on skin cancer datasets, achieving individual accuracies ranging from 77.20% to 91.90%. Our method leverages the synergistic capabilities of these models by combining their complementary features to elevate classification performance further. In our approach, input images undergo preprocessing for model compatibility. The ensemble integrates the pre-trained models with their architectures and weights preserved. For each skin lesion image under examination, every model produces a prediction. These are subsequently aggregated using the max voting ensemble technique to yield the final classification, with the majority-voted class serving as the conclusive prediction. Through comprehensive testing on a diverse dataset, our ensemble outperformed individual models, attaining an accuracy of 93.18% and an AUC score of 0.9320, thus demonstrating superior diagnostic reliability and accuracy. We evaluated the effectiveness of our proposed method on the HAM10000 dataset to ensure its generalizability. Our ensemble method delivers a robust, reliable, and effective tool for the classification of skin cancer. By utilizing the power of advanced deep neural networks, we aim to assist healthcare professionals in achieving timely and accurate diagnoses, ultimately reducing mortality rates and enhancing patient outcomes.

@article{hossain2024combining,
  author = {Hossain, M.M. and Hossain, M.M. and Arefin, M.B. and Akhtar, F. and Blake, John},
  title = {Combining State-of-the-Art Pre-Trained Deep Learning Models: A Noble Approach for Skin Cancer Detection Using Max Voting Ensemble},
  year = {2024},
  journal = {Diagnostics},
  volume = {14},
  number = {1},
  doi = {10.3390/diagnostics14010089}
}

Hossain, M., Hossain, M., Arefin, M., Akhtar, F., & Blake, J. (2024). Combining State-of-the-Art Pre-Trained Deep Learning Models: A Noble Approach for Skin Cancer Detection Using Max Voting Ensemble. Diagnostics, 14(1). https://doi.org/10.3390/diagnostics14010089

This study evaluates a computerized dynamic assessment (C-DA) method's potential to build a detailed pragmatics-focused developmental profile of a Japanese L2 English learner's L2 email writing. L2 email writing studies typically separate learning and assessment, using holistic scales to evaluate the pragmatic elements of learner texts. C-DA, grounded in sociocultural theory, unifies learning and assessment, administering email tasks with varying social contexts and providing immediate mediation within the learner's zone of proximal development (ZPD). Further, a diagnostic capacity allows for identification of specific pragmatics-related infelicities. The C-DA employs a dual-layered framework: an identification layer uses a coding scheme to automatically identify specific instances of perceived pragmatic inappropriateness, while the mediation layer provides ZPD-sensitive mediation. By evaluating the frequency and explicitness of mediation engaged in, in combination with qualitative examination of elicited email texts, the C-DA enables insights into learner development within the ZPD. We focus on an individual learner's interaction with the C-DA, evaluating the program's effectiveness in enabling a detailed learner diagnostic and developmental profile.

@article{nicholas2024profiling,
  author = {Nicholas, A. and Blake, John},
  title = {Profiling learner development through the application of a computerized dynamic assessment methodology to a Japanese learner's L2 English email writing},
  year = {2024},
  journal = {Research Methods in Applied Linguistics},
  volume = {3},
  number = {3},
  doi = {10.1016/j.rmal.2024.100164}
}

Nicholas, A., & Blake, J. (2024). Profiling learner development through the application of a computerized dynamic assessment methodology to a Japanese learner's L2 English email writing. Research Methods in Applied Linguistics, 3(3). https://doi.org/10.1016/j.rmal.2024.100164

This paper examines the plateau effect and the role of Computer-Assisted Pronunciation Training (CAPT) in enabling learners to move beyond the plateau. Specifically, the samples and empirical evidence for this study is provided by StudyIntonation, a top-down CAPT environment supporting visual display of phrasal intonation in the form of pitch graphs presented for both the model pitch of native speakers and attempts of learners. Utterances of model speakers are grouped by situational context, prosodic forms and mode of feedback. The system largely relies upon concepts of sociocultural theory, such as mediation through the zone of proximal development. With the help of an experimental group of high school students, we use mathematical models to pinpoint the Zone of Proximal Development (ZPD), allowing for delivery of tailored task classification based on syntax and discourse tags. Longitudinal pronunciation assessment supported by dynamic time warping and cross-recurrence quantification analysis is used to locate the ZPD, and provide personalized practice. Preliminary experiments for the current study demonstrate that this approach can help learners in overcoming the plateau effect experienced during the learning process. The reported new findings create further grounds for improving and targeting the CAPT system feedback to learners with respect to their individual achievements and differences in learning styles.

@article{pyshkin2024moving,
  author = {Pyshkin, E. and Blake, John and Bogach, N.},
  title = {Moving beyond the plateau with computer-assisted pronunciation mediation},
  year = {2024},
  journal = {International Journal of Information and Education Technology},
  volume = {14},
  number = {6},
  pages = {890--897},
  doi = {10.18178/ijiet.2024.14.6.2115}
}

Pyshkin, E., Blake, J., & Bogach, N. (2024). Moving beyond the plateau with computer-assisted pronunciation mediation. International Journal of Information and Education Technology, 14(6), 890-897. https://doi.org/10.18178/ijiet.2024.14.6.2115

@article{nicholas2023investigating,
  author = {Nicholas, A. and Blake, John and Mozgovoy, M. and Perkins, J.},
  title = {Investigating pragmatic failure in L2 English email writing among Japanese university EFL learners: A learner corpus approach},
  year = {2023},
  journal = {Register Studies},
  volume = {5},
  number = {1},
  pages = {23--51},
  doi = {10.1075/rs.20016.nic}
}

Nicholas, A., Blake, J., Mozgovoy, M., & Perkins, J. (2023). Investigating pragmatic failure in L2 English email writing among Japanese university EFL learners: A learner corpus approach. Register Studies, 5(1), 23-51. https://doi.org/10.1075/rs.20016.nic

@article{mikhailava2022language,
  author = {Mikhailava, V. and Lesnichaia, M. and Bogach, N. and Lezhenin, I. and Blake, John and Pyshkin, E.},
  title = {Language accent detection with CNN using sparse data from a crowd-sourced speech archive},
  year = {2022},
  journal = {Mathematics},
  volume = {10},
  number = {16},
  pages = {2913},
  doi = {10.3390/math10162913}
}

Mikhailava, V., Lesnichaia, M., Bogach, N., Lezhenin, I., Blake, J., & Pyshkin, E. (2022). Language accent detection with CNN using sparse data from a crowd-sourced speech archive. Mathematics, 10(16), 2913. https://doi.org/10.3390/math10162913

In programming classes, instructors need to work with numerous exercise submissions to verifywhetherthesubmittedsourcecodemeetstherequirements,andwhetherthereisany unauthorizedborrowingofcodefragments. Thecheckingprocedureislaboriousrequiring much unproductive effort and time. However, ignoring instances of potential plagiarism may negatively impact learner motivation. Despite the existence of practical tools devel- oped for software testing and similarity detection, there are still issues in developing an open-sourcesubmissionassessmentsystemthatwouldstreamlinetheclassroomworkflow. Thispaperdescribesapracticalsubmissionassessmentsystemthatreducesthetimeteach- ersspendcheckingthesolutionssubmittedbystudents.

@article{mozgovoy2022teacher-oriented,
  author = {Mozgovoy, M. and Pyshkin, E. and Blake, John and Purgina, M. and Leung, A.},
  title = {Teacher-oriented source code similarity detection and visualization for programming assignments},
  year = {2022},
  journal = {IIAI Letters on Informatics and Interdisciplinary Research},
  volume = {2},
  pages = {82},
  doi = {10.52731/liir.v002.082}
}

Mozgovoy, M., Pyshkin, E., Blake, J., Purgina, M., & Leung, A. (2022). Teacher-oriented source code similarity detection and visualization for programming assignments. IIAI Letters on Informatics and Interdisciplinary Research, 2, 82. https://doi.org/10.52731/liir.v002.082

@article{blake2021asynchronous,
  author = {Blake, John},
  title = {Asynchronous peer teaching using student-created multimodal materials},
  year = {2021},
  journal = {International Journal of Information and Education Technology},
  volume = {11},
  number = {6},
  pages = {286--291},
  doi = {10.18178/ijiet.2021.11.6.1524}
}

Blake, J. (2021). Asynchronous peer teaching using student-created multimodal materials. International Journal of Information and Education Technology, 11(6), 286-291. https://doi.org/10.18178/ijiet.2021.11.6.1524

@article{blake2021developing,
  author = {Blake, John},
  title = {Developing critical readers},
  year = {2021},
  journal = {Journal of Communication and Education},
  volume = {5},
  number = {1},
  pages = {12--24}
}

Blake, J. (2021). Developing critical readers. Journal of Communication and Education, 5(1), 12-24.

@article{bogach2021speech,
  author = {Bogach, N. and Boitsova, E. and Chernonog, S. and Lamtev, A. and Lesnichaya, M. and Lezhenin, I. and Novopashenny, A. and Svechnikov, R. and Tsikach, D. and Vasiliev, K. and Pyshkin, E. and Blake, John},
  title = {Speech Processing for Language Learning: A Practical Approach to Computer-Assisted Pronunciation Teaching},
  year = {2021},
  journal = {Electronics},
  volume = {10},
  number = {3},
  pages = {235},
  doi = {10.3390/electronics10030235}
}

Bogach, N., Boitsova, E., Chernonog, S., Lamtev, A., Lesnichaya, M., Lezhenin, I., Novopashenny, A., Svechnikov, R., Tsikach, D., Vasiliev, K., Pyshkin, E., & Blake, J. (2021). Speech Processing for Language Learning: A Practical Approach to Computer-Assisted Pronunciation Teaching. Electronics, 10(3), 235. https://doi.org/10.3390/electronics10030235

@article{yasuta2021developing,
  author = {Yasuta, T. and Blake, John},
  title = {Developing transferable writing skills through manga},
  year = {2021},
  journal = {Second Language Research and Practice},
  volume = {2},
  number = {1},
  pages = {129--139}
}

Yasuta, T., & Blake, J. (2021). Developing transferable writing skills through manga. Second Language Research and Practice, 2(1), 129-139.

A purpose-built online error detection tool was developed to provide genre-specific corpus- based feedback on errors occurring in draft research articles and graduation theses. The primary envisaged users were computer science majors studying at a public university in Japan. This article discusses the development and evaluation of this interactive, multimodal tool. An in-house learner corpus of graduation theses was annotated for errors that affect the accuracy, brevity, clarity, objectivity and formality of scientific research writing. Software was developed to identify the errors discovered and provide learners with actionable advice and multimodal explanations in both English and Japanese. Qualitative evaluation received in usability studies and focus groups from both teachers and students was extremely positive. Preliminary quantitative evaluation of the effectiveness of the error detector was conducted. Through this pedagogic tool, learners can receive immediate actionable feedback on potential errors, and their teachers no longer feel obliged to check for common genre-specific errors.

@article{blake2020genre-specific,
  author = {Blake, John},
  title = {Genre-specific error detection with multimodal feedback},
  year = {2020},
  journal = {RELC Journal},
  volume = {51},
  number = {1},
  pages = {179--187},
  doi = {10.1177/0033688219898282}
}

Blake, J. (2020). Genre-specific error detection with multimodal feedback. RELC Journal, 51(1), 179-187. https://doi.org/10.1177/0033688219898282

@article{purgina2020wordbricks,
  author = {Purgina, M. and Mozgovoy, M. and Blake, John},
  title = {WordBricks: Mobile Technology and Visual Grammar Formalism for Gamification of Natural Language Grammar Acquisition},
  year = {2020},
  journal = {Journal of Educational Computing Research},
  volume = {58},
  number = {1},
  pages = {126--159},
  doi = {10.1177/0735633119833010}
}

Purgina, M., Mozgovoy, M., & Blake, J. (2020). WordBricks: Mobile Technology and Visual Grammar Formalism for Gamification of Natural Language Grammar Acquisition. Journal of Educational Computing Research, 58(1), 126-159. https://doi.org/10.1177/0735633119833010

@article{pyshkin2020a,
  author = {Pyshkin, E.V. and Blake, John},
  title = {A metaphoric bridge: Understanding software engineering through literature and fine arts},
  year = {2020},
  journal = {Terra Linguistica},
  volume = {11},
  number = {3},
  pages = {59--77}
}

Pyshkin, E., & Blake, J. (2020). A metaphoric bridge: Understanding software engineering through literature and fine arts. Terra Linguistica, 11(3), 59-77. https://human.spbstu.ru/en/article/2020.41.5/

Automated API documentation and test generation for Python web applications remain challenging due to the fragmentation of the framework ecosystem and the limitations of existing single-framework tools. We present a framework-adaptive multi-agent pipeline supporting seven Python web frameworks — Django, FastAPI, Flask, Bottle, Tornado, Pyramid, and Sanic — through dedicated static parsers and framework-specific prompt templates. A rule-based parsing layer extracts per-endpoint context without invoking any language model. A Generation Agent then produces structured parameter documentation, which a Validation Agent independently verifies through up to three revision rounds; endpoints that fail verification are flagged for human review rather than passed forward silently. A Consistency Agent subsequently identifies cross-endpoint inconsistencies across the complete document set. A Test Generation Agent further produces test intents and pytest skeletons for each confirmed endpoint. Evaluation across all seven frameworks demonstrates robust detection and extraction performance, and analysis of validation false positives reveals four distinct failure categories with targeted remediation strategies identified for future refinement.

@inproceedings{zhao2026framework,
  author = {Zhao, Peng and Blake, John and Pyshkin, E.},
  title = {Framework-Adaptive Agentic Pipelines for API Knowledge Extraction and Test Generation},
  year = {2026},
  booktitle = {IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology}
}

Zhao, P., Blake, J., & Pyshkin, E. (2026). Framework-Adaptive Agentic Pipelines for API Knowledge Extraction and Test Generation. In IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology.

@inproceedings{author2026genre,
  author = {Author, A. and Blake, John and Author, A. and Author, A.},
  title = {Genre-Residualized Authorship Attribution Model: Mitigating Cross-Genre Effects under Data Scarcity},
  year = {2026}
}

Author, A., Blake, J., Author, A., & Author, A. (2026). Genre-Residualized Authorship Attribution Model: Mitigating Cross-Genre Effects under Data Scarcity. In .

@inproceedings{author2026grounded-theory-inspired,
  author = {Author, An and Blake, John and Author, Another},
  title = {Grounded-Theory-Inspired Human-Led Agentic Pipeline for Qualitative Analysis: A Proof-of-Concept},
  year = {2026},
  booktitle = {18th International Conference on Human System Interaction}
}

Author, A., Blake, J., & Author, A. (2026). Grounded-Theory-Inspired Human-Led Agentic Pipeline for Qualitative Analysis: A Proof-of-Concept. In 18th International Conference on Human System Interaction.

Authorship analysis is a challenging computational and linguistic task, which harnesses linguistic evidence to profile, verify, or attribute authorship. In forensic contexts, this task is complicated by limited and non-representative data, adversarial writing conditions (e.g. stylistic obfuscation), cross-genre comparison, and the requirements imposed by legal frameworks such as the Daubert criteria. A three-tier taxonomy of approaches is introduced, comprising expert-driven interpretive approaches, analytical similarity-based approaches, and predictive model-based approaches. Within this taxonomy, nine core methods are identified, ranging from expert linguistic reasoning and rule-based analysis to statistical, stylometric, machine-learning, deep-learning, LLM-based, and multi-agent pipeline approaches. The framework is sufficiently flexible to accommodate emerging analytical techniques. The paper concludes by arguing for an eclectic, evidence-aware approach to authorship analysis that prioritizes transparency and contextual validity.

@inproceedings{blake2026authorship,
  author = {Blake, John},
  title = {Authorship Analysis in the Age of AI: From Expert Reasoning to Multi-Agent Pipelines},
  year = {2026},
  booktitle = {Proceedings of the 14th International Conference on Information and Education Technology}
}

Blake, J. (2026). Authorship Analysis in the Age of AI: From Expert Reasoning to Multi-Agent Pipelines. In Proceedings of the 14th International Conference on Information and Education Technology.

This paper introduces a dual-mode n-gram similarity detection tool specifically designed for corpus-based forensic authorship analysis. Intra-corpus mode is used to verify consistency within a dataset while inter-corpus mode is for comparison to a questioned dataset. Preliminary accuracy evaluation of shared n-gram detection is perfect at 100%.

@inproceedings{blake2026dual-mode,
  author = {Blake, John and Tamura, K. and Kredens, K.},
  title = {Dual-mode N-gram Similarity Detection for Forensic Authorship Analysis},
  year = {2026},
  booktitle = {Proceedings for 39th Pacific Asia Conference on Language, Information and Computation (PACLIC 39)}
}

Blake, J., Tamura, K., & Kredens, K. (2026). Dual-mode N-gram Similarity Detection for Forensic Authorship Analysis. In Proceedings for 39th Pacific Asia Conference on Language, Information and Computation (PACLIC 39).

@inproceedings{author2026human-verifiable,
  author = {Author, An and Blake, John and Another, Another},
  title = {Human-Verifiable API Documentation Generation for Legacy Web Frameworks Using Multi-Agent LLMs},
  year = {2026}
}

Author, A., Blake, J., & Another, A. (2026). Human-Verifiable API Documentation Generation for Legacy Web Frameworks Using Multi-Agent LLMs. In undefined.

Passive voice constructions vary in how explicitly they represent the agent, or doer of the action, ranging from clauses with fully stated agents to instances where the agent is omitted or difficult to infer. This paper introduces a multi-agentic system designed to automatically categorize English passive voice instances according to a four-level mystification index. The index ranges from Level 1, where the agent is explicitly stated, to Level 4, where the agent is maximally mystified, i.e., omitted and unrecoverable to casual readers without specialized knowledge. The system is implemented using LangChain and LangGraph, integrating PassivePy with multiple specialized agents dedicated to subtasks such as agent detection, inference, verification, and classification. Evaluation was conducted using manually annotated newspaper editorials. Results show that the system performs at expert-level accuracy when agents are explicit or guessable with certainty (Levels 1 and 2), while performance drops sharply in ambiguous or unknown cases (Levels 3 and 4). These findings demonstrate both the feasibility of automatic mystification analysis and the potential for future improvements in handling highly ambiguous contexts.

@inproceedings{blake2026multi-agentic,
  author = {Blake, John and Lingle, W. and Nguyen, D.T. and Pyshkin, E.},
  title = {Multi-agentic Automated Classification of Passive Voice Constructions by Mystification Level},
  year = {2026},
  booktitle = {Proceedings of the 20th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP 2025)},
  doi = {10.1109/iSAI-NLP66160.2025.11320469}
}

Blake, J., Lingle, W., Nguyen, D., & Pyshkin, E. (2026). Multi-agentic Automated Classification of Passive Voice Constructions by Mystification Level. In Proceedings of the 20th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP 2025). https://doi.org/10.1109/iSAI-NLP66160.2025.11320469

This paper presents the design and construction of WikiFirst, a corpus for investigating the impact of content variation on authorship similarity under a fixed genre. Prior work has investigated individual authorial style and impact of genre. However, the role of content has remained underexplored due to the lack of suitable data. We address this gap by constructing a Wikipedia-based corpus consisting exclusively of first revisions authored by non-anonymous editors, thereby ensuring high authorship certainty while maintaining a stable encyclopaedic genre.

@inproceedings{nguyen2026wikifirst,
  author = {Nguyen, D.T. and Sat, C.G. and Blake, John and Pyshkin, E.},
  title = {WikiFirst: A Genre-Fixed, Content-controlled Corpus for Evaluating Content Effects in Authorship Analysis},
  year = {2026},
  booktitle = {Proceedings of 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature co-located at the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2026), (pp},
  pages = {323--327}
}

Nguyen, D., Sat, C., Blake, J., & Pyshkin, E. (2026). WikiFirst: A Genre-Fixed, Content-controlled Corpus for Evaluating Content Effects in Authorship Analysis. In Proceedings of 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature co-located at the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2026), (pp (pp. 323--327).

The creation of high-quality multiple-choice questions (MCQs) for language assessment is a labour-intensive task, often requiring careful balancing of linguistic appropriacy, proficiency level, topic coverage, and distractor plausibility. We present a modular, multi-agentic system built using LangChain to generate appropriate MCQs. Each agent in the system is responsible for a distinct task in the question generation pipeline. These tasks range from topic selection and question formation to answer validation, distractor generation, and coverage checks. The system supports flexible substitution of Large Language Models (LLMs), allowing comparative benchmarking across tasks in terms of generation accuracy and latency. Human expert assessment of item quality confirmed that the best-performing configurations yielded scores exceeding 95% in grammatical correctness with satisfactory speed. Our results demonstrate that multi-agent LLM-based architectures can effectively automate complex educational content creation workflows while offering transparency, modularity, and fine-grained controllability. The proposed system offers a reusable design pattern for intelligent educational content generation in broader domains.

@inproceedings{zhao2026a,
  author = {Zhao, P. and Blake, John and Pyshkin, E.},
  title = {A Modular Multi-Agentic Architecture for Automating Multiple-Choice Question Generation in Language Assessment},
  year = {2026},
  booktitle = {Proceedings of 7th International Conference on AI in Computational Linguistics, Procedia Computer Science, Elsevier},
  doi = {10.1016/j.procs.2026.01.070}
}

Zhao, P., Blake, J., & Pyshkin, E. (2026). A Modular Multi-Agentic Architecture for Automating Multiple-Choice Question Generation in Language Assessment. In Proceedings of 7th International Conference on AI in Computational Linguistics, Procedia Computer Science, Elsevier. https://doi.org/10.1016/j.procs.2026.01.070

This chapter examines the challenges and opportunities presented by generative artificial intelligence (AI) in language education, focusing on its implications for policy development. Drawing on case studies of English language learners in Japan, the discussion highlights how generative AI tools can enhance learning by providing instant feedback, fostering critical engagement, and aiding technical communication. However, the misuse of AI to produce polished texts with minimal effort raises ethical concerns about academic integrity, fairness, and technological dependency. Three policy approaches are examined: banning generative AI, allowing its use, and actively encouraging its integration into educational practices. The chapter concludes that embracing generative AI in education, with appropriate guidance and training, prepares students to navigate AI-integrated environments effectively and ethically, aligning with the broader goal of equipping learners for a future shaped by technological advancements.

@inproceedings{blake2025policies,
  author = {Blake, John},
  title = {Policies for Generative AI in Language Education: Challenges and Choices},
  year = {2025},
  booktitle = {Proceedings of HKAECT 2025},
  publisher = {Springer}
}

Blake, J. (2025). Policies for Generative AI in Language Education: Challenges and Choices. In Proceedings of HKAECT 2025. Springer.

We present VR Math Bridge, a virtual reality (VR)-based application designed to enhance calculus education by combining immersive virtual environments with artificial intelligence (AI)-driven teaching assistance. VR Math Bridge creates a virtual classroom where students interact with Khan Academy videos and a 3D AI assistant that provides real-time, personalized feedback to their questions. This system leverages a floating panel for chapter selection, a virtual blackboard for video playback, and Cognitive 3D for analyzing user engagement. To demonstrate the system’s capabilities, we developed a prototype on Quest 3, focusing on derivatives as the initial test topic. We conducted a preliminary subjective evaluation (n=2) of the prototype to collect early insights for future user study evaluation.

@inproceedings{lai2025vr,
  author = {Lai, H.S. and Nassani, A. and Blake, John and Villegas, J.},
  title = {VR Math Bridge: Bridging Interactivity in Online Education with AI and VR},
  year = {2025},
  booktitle = {Proceedings of the IEEE Gaming, Entertainment, and Media Conference (IEEE GEM 2025)},
  publisher = {IEEE},
  doi = {10.1109/GEM66882.2025.11155841}
}

Lai, H., Nassani, A., Blake, J., & Villegas, J. (2025). VR Math Bridge: Bridging Interactivity in Online Education with AI and VR. In Proceedings of the IEEE Gaming, Entertainment, and Media Conference (IEEE GEM 2025). IEEE. https://doi.org/10.1109/GEM66882.2025.11155841

We introduce a novel approach to language learning leveraging digital humans as adaptive tutors within immersive XR environments. Our system’s novelty lies in the use of biosignals, specifically real-time heart rate data, collected from a Samsung Watch 7, to dynamically adapt the learning experience. The digital human tutor adjusts its behavior, feedback, and the difficulty of the learning content based on the learner’s inferred cognitive and emotional state. We present the fully developed system architecture, which integrates a customizable digital human powered by ConvAI, LLM, an XR environments, and a data streaming pipeline. While human participant testing is planned, preliminary insights from the system’s development demonstrate the technical feasibility of this approach. This research has the potential to significantly enhance language learning outcomes, engagement, and motivation by creating more personalized, and engaging learning experiences, paving the way for a new generation of adaptive educational technologies.

@inproceedings{nassani2025adaptive,
  author = {Nassani, A. and Blake, John and Villegas, J.},
  title = {Adaptive Learning Companions: Enhancing Education with Biosignal-Driven Digital Human},
  year = {2025},
  booktitle = {Proceedings of the Extended Abstracts of the Conference on Human Factors in Computing Systems, CHI 2025},
  doi = {10.1145/3706599.3719877}
}

Nassani, A., Blake, J., & Villegas, J. (2025). Adaptive Learning Companions: Enhancing Education with Biosignal-Driven Digital Human. In Proceedings of the Extended Abstracts of the Conference on Human Factors in Computing Systems, CHI 2025. https://doi.org/10.1145/3706599.3719877

In this paper, we provide a proof-of-concept for a computerized diagnostic language assessment (C-DLA) of spoken requesting among Japanese learners of English at a Japanese computer science university. The program focuses on the pragmatics aspect of spoken communication, in which the language choices we make are affected by socio-contextual factors such as relative social status and familiarity with the interlocutor. In so doing, the C-DLA aims to address a number of challenges. Requesting is an important, but challenging skill for many learners, and yet is also undertaught in the language classroom, due to time and resource constraints. Further, assessments typically evaluate the learner holistically, providing an overall score, without providing insight into specific aspects of the learner's performance. A C-DLA addresses these challenges by employing a three-stage process: i) assessment administration; ii) provision of immediate individualized feedback to the learner that promotes learning, and iii) further instruction provision, based on the assessment results. Computerization of the DLA widens access, allowing large numbers of learners to engage with the program simultaneously. Here, we provide a rationale for the C-DLA and an outline of the key challenges — namely, speech recognition of L2 English, identification of pragmatic inappropriateness in a learner's interactive speaking performance and automated feedback delivery. We further provide a proof-of-concept for the C-DLA, in which the program administers a number of interactive spoken requesting tasks to the learner, acts as an automated spoken dialogue interlocutor, and provides immediate, automated pragmatics-focused feedback when necessary.

@inproceedings{nicholas2025computerized,
  author = {Nicholas, A. and Mozgovoy, M. and Blake, John},
  title = {Computerized Diagnostic Language Assessment of Oral Requesting-in-interaction: Proof-of-concept},
  year = {2025},
  booktitle = {Proceedings of 13th International Conference on Information and Education Technology},
  publisher = {IEEE Xplore},
  doi = {10.1109/ICIET66371.2025.11046328}
}

Nicholas, A., Mozgovoy, M., & Blake, J. (2025). Computerized Diagnostic Language Assessment of Oral Requesting-in-interaction: Proof-of-concept. In Proceedings of 13th International Conference on Information and Education Technology. IEEE Xplore. https://doi.org/10.1109/ICIET66371.2025.11046328

@inproceedings{pyshkin2025virtualization,
  author = {Pyshkin, E. and Sato, R. and Nassani, A. and Blake, John},
  title = {Virtualization for Kintsugi Art: Damaged Porcelain Figurine Recreation Supported by 3D Modeling Computer Technology},
  year = {2025},
  booktitle = {Proceedings of ARTeFACTo 2024: 4th International Conference on Digital Creation in Arts, Media and Technology}
}

Pyshkin, E., Sato, R., Nassani, A., & Blake, J. (2025). Virtualization for Kintsugi Art: Damaged Porcelain Figurine Recreation Supported by 3D Modeling Computer Technology. In Proceedings of ARTeFACTo 2024: 4th International Conference on Digital Creation in Arts, Media and Technology. https://books.usj.edu.mo/index.php/usj-acaedemicpress/catalog/book/27

This paper explores the extent to which stylistic features contribute to the task of authorship attribution in forensic contexts. Drawing on a filtered subset of the Enron email corpus, the study operationalizes stylistic indicators across four groups: lexical, syntactic, orthographic, and discoursal. Using R Programming Language for feature engineering and logistic regression modelling, we systematically assessed both the individual and interactive effects of these features on attribution accuracy. Results show that n-gram similarity consistently outperformed all other features, with the combined model of n-gram similarity and its interaction with other features achieving accuracy, precision and F1 scores of 91.6%, 93.3% and 91.7% respectively. The model was subsequently evaluated on a subset of the TEL corpus to assess its applicability in a forensic setting. The findings highlight the dominant role of lexical similarity and suggest that integrating interaction effects can yield further performance gains in forensic authorship analysis.

@inproceedings{sat2025modelling,
  author = {Sat, G.C. and Blake, John and Pyshkin, E.},
  title = {Modelling the Relative Contributions of Stylistic Features in Forensic Authorship Attribution},
  year = {2025},
  booktitle = {Proceedings for the Recent Advances in Natural Language Processing 2025 Conference}
}

Sat, G., Blake, J., & Pyshkin, E. (2025). Modelling the Relative Contributions of Stylistic Features in Forensic Authorship Attribution. In Proceedings for the Recent Advances in Natural Language Processing 2025 Conference. https://acl-bg.org/proceedings/2025/RANLP%202025/index.html

The emerging field of virtual reality (VR) therapies in diverse therapeutic settings is examined in this chapter's investigation. We provide the most recent literature highlighting an important developments and obstacles in VR therapy research. There are two innovative approaches introduced: a VR-based motor rehabilitation program for stroke patients and an adaptive VR experience rehabilitation scheme for concern disorders. The machine learning algorithms and highly developed haptic feedback are used in this method to improve the treatment results. The result of the proposed approach is compared with the conventional therapeutic approaches. Our proposed system shows a major improvement in both patient engagement and treatment efficiency. The proposed approaches leverage the immersive capabilities of the healthcare metaverse to deliver personalized VR-based motor rehabilitation for stroke patients and adaptive VR exposure therapy for anxiety disorders, utilizing machine learning algorithms and advanced haptic feedback to create a seamless, interactive therapeutic environment that significantly enhances patient engagement and treatment efficacy compared to conventional methods. Many more personalized and successful therapeutic interventions are made possible by the research, which contributes to the continuous development of VR treatments.

@inproceedings{sungheetha2025adaptive,
  author = {Sungheetha, A. and Sharma, R.R. and Blake, John and Sreeja, B.P.},
  title = {Adaptive virtual reality exposure therapy and motor rehabilitation from Hebbian learning rule in metaverse},
  year = {2025},
  booktitle = {In Healthcare Frontiers in the Metaverse: Innovations and Impacts, (pp. 227-243)},
  pages = {227--243},
  doi = {10.1016/B978-0-443-32998-2.00017-2}
}

Sungheetha, A., Sharma, R., Blake, J., & Sreeja, B. (2025). Adaptive virtual reality exposure therapy and motor rehabilitation from Hebbian learning rule in metaverse. In In Healthcare Frontiers in the Metaverse: Innovations and Impacts, (pp. 227-243) (pp. 227-243). https://doi.org/10.1016/B978-0-443-32998-2.00017-2

@inproceedings{sungheetha2025analysis,
  author = {Sungheetha, A. and Blake, John and Adere, K. and Shifaw, B.},
  title = {Analysis and identification of gout flares using machine learning},
  year = {2025},
  booktitle = {In Diagnosing Musculoskeletal Conditions using Artifical Intelligence and Machine Learning to Aid Interpretation of Clinical Imaging, (pp. 179-194)},
  pages = {179--194},
  doi = {10.1016/B978-0-443-32892-3.00010-5}
}

Sungheetha, A., Blake, J., Adere, K., & Shifaw, B. (2025). Analysis and identification of gout flares using machine learning. In In Diagnosing Musculoskeletal Conditions using Artifical Intelligence and Machine Learning to Aid Interpretation of Clinical Imaging, (pp. 179-194) (pp. 179-194). https://doi.org/10.1016/B978-0-443-32892-3.00010-5

@inproceedings{sungheetha2025smart,
  author = {Sungheetha, A. and Mahapatra, S. and Blake, John and Aroba, O.J. and Ghantasala, G.S.P.},
  title = {Smart Underwater Acoustic Monitoring with Knowledge Distillation and FOPT Feature Fusion for Optimization},
  year = {2025},
  booktitle = {Proceedings of the 2nd International Conference on New Frontiers in Communication, Automation, Management and Security},
  doi = {10.1109/ICCAMS65118.2025.11234166}
}

Sungheetha, A., Mahapatra, S., Blake, J., Aroba, O., & Ghantasala, G. (2025). Smart Underwater Acoustic Monitoring with Knowledge Distillation and FOPT Feature Fusion for Optimization. In Proceedings of the 2nd International Conference on New Frontiers in Communication, Automation, Management and Security. https://doi.org/10.1109/ICCAMS65118.2025.11234166

@inproceedings{pyshkin2024multimodal,
  author = {Pyshkin, E. and Blake, John and Khaustova, V. and Khaustov, V. and Lezhenin, I. and Svechnikov, R. and Bogach, N.},
  title = {Multimodal contextualizing and targeting exercises in iCAPT system},
  year = {2024},
  booktitle = {Proceedings of INTED 2024, (pp},
  pages = {438--448},
  publisher = {IATED},
  doi = {10.21125/inted.2024.0164}
}

Pyshkin, E., Blake, J., Khaustova, V., Khaustov, V., Lezhenin, I., Svechnikov, R., & Bogach, N. (2024). Multimodal contextualizing and targeting exercises in iCAPT system. In Proceedings of INTED 2024, (pp (pp. 438-448). IATED. https://doi.org/10.21125/inted.2024.0164

@inproceedings{pyshkin2024transfigured,
  author = {Pyshkin, E. and Sato, R. and Nassani, A. and Blake, John},
  title = {"Transfigured Reminiscence": A Vintage Porcelain Figurine Reborn Through 3D Virtualization and Kintsugi Art},
  year = {2024},
  booktitle = {Proceedings of the 5th Kyoto Conference on Arts, Media and Culture, (pp},
  pages = {179--187},
  doi = {10.22492/issn.2436-0503.2024.17}
}

Pyshkin, E., Sato, R., Nassani, A., & Blake, J. (2024). "Transfigured Reminiscence": A Vintage Porcelain Figurine Reborn Through 3D Virtualization and Kintsugi Art. In Proceedings of the 5th Kyoto Conference on Arts, Media and Culture, (pp (pp. 179-187). https://doi.org/10.22492/issn.2436-0503.2024.17

@inproceedings{tamura2024finer-grained,
  author = {Tamura, K. and Blake, John},
  title = {Finer-grained part-of-speech classification of adjectives},
  year = {2024},
  booktitle = {Proceedings of The Japanese Society for Language Sciences 25th Annual International Conference (pp},
  pages = {182--183}
}

Tamura, K., & Blake, J. (2024). Finer-grained part-of-speech classification of adjectives. In Proceedings of The Japanese Society for Language Sciences 25th Annual International Conference (pp (pp. 182-183).

@inproceedings{blake2023automatic,
  author = {Blake, John and Pyshkin, E. and Pavlic, S.},
  title = {Automatic detection and visualization of information structure in English},
  year = {2023},
  booktitle = {Proceedings of the 6th International Conference on Natural Language Processing and Information Retrieval},
  pages = {200--204},
  publisher = {ACM},
  doi = {10.1145/3582768.3582784}
}

Blake, J., Pyshkin, E., & Pavlic, S. (2023). Automatic detection and visualization of information structure in English. In Proceedings of the 6th International Conference on Natural Language Processing and Information Retrieval (pp. 200-204). ACM. https://doi.org/10.1145/3582768.3582784

@inproceedings{blake2023linguistic-first,
  author = {Blake, John and Tamura, K. and Pyshkin, E.},
  title = {Linguistic-first approach to learning Python for natural language generation: Problem breakdown to pseudocode},
  year = {2023},
  booktitle = {Conference Proceedings of the 5th International Conference on ICT Integration in Technical Education, 2909 (1), 020002},
  pages = {020002},
  doi = {10.1063/5.0183649}
}

Blake, J., Tamura, K., & Pyshkin, E. (2023). Linguistic-first approach to learning Python for natural language generation: Problem breakdown to pseudocode. In Conference Proceedings of the 5th International Conference on ICT Integration in Technical Education, 2909 (1), 020002 (pp. 020002). https://doi.org/10.1063/5.0183649

This article shows how a service quality model can be applied by language teachers to improve student satisfaction. Improvements in student satisfaction, however, do not necessary correlate with improvements in teaching ability. Exceeding the low expectations of students results in high degrees of satisfaction, but meeting the high expectations of students may not result in satisfaction. This article introduces the theoretical background, presents a model of service quality for language teaching, and shows how this model can be applied through three case studies. The article concludes with practical suggestions on how teachers of language can increase student satisfaction levels by meeting and exceeding the expectations of students.

@inproceedings{blake2023surprise,
  author = {Blake, John},
  title = {Surprise and delight: Application of a service quality model to language teaching},
  year = {2023},
  booktitle = {Proceedings (pp},
  pages = {5616--5623},
  doi = {10.21125/inted.2023.1467}
}

Blake, J. (2023). Surprise and delight: Application of a service quality model to language teaching. In Proceedings (pp (pp. 5616-5623). https://doi.org/10.21125/inted.2023.1467

@inproceedings{carr2023pronunciation,
  author = {Carr, N. and Blake, John},
  title = {Pronunciation Scaffolder 3.0: A User Experience and Usability Study},
  year = {2023},
  booktitle = {Proceedings of the 16th International Conference on E-Service and Knowledge Management within14th IIAI International Congress on Advanced Applied Informatics, (pp},
  pages = {29--34},
  publisher = {IEEE},
  doi = {10.1109/IIAI-AAI59060.2023.00016}
}

Carr, N., & Blake, J. (2023). Pronunciation Scaffolder 3.0: A User Experience and Usability Study. In Proceedings of the 16th International Conference on E-Service and Knowledge Management within14th IIAI International Congress on Advanced Applied Informatics, (pp (pp. 29-34). IEEE. https://doi.org/10.1109/IIAI-AAI59060.2023.00016

@inproceedings{pyshkin2023multimodal,
  author = {Pyshkin, E. and Kusakari, A. and Blake, John and Pham, N.B. and Bogach, N.},
  title = {Multimodal Modeling of the Mora-timed Rhythm of Japanese and its Application to Computer-assisted Pronunciation Training},
  year = {2023},
  booktitle = {Proceedings of the 14th International Conference on Learning Technologies and Learning Environments within 14th IIAI International Congress on Advanced Applied Informatics, (pp},
  pages = {174--179},
  publisher = {IEEE},
  doi = {10.1109/IIAI-AAI59060.2023.00044}
}

Pyshkin, E., Kusakari, A., Blake, J., Pham, N., & Bogach, N. (2023). Multimodal Modeling of the Mora-timed Rhythm of Japanese and its Application to Computer-assisted Pronunciation Training. In Proceedings of the 14th International Conference on Learning Technologies and Learning Environments within 14th IIAI International Congress on Advanced Applied Informatics, (pp (pp. 174-179). IEEE. https://doi.org/10.1109/IIAI-AAI59060.2023.00044

@inproceedings{pyshkin2023music,
  author = {Pyshkin, E. and Kusakari, A. and Blake, John and Bogach, N.},
  title = {Music and Choreography Metaphors in Spoken Language Rhythm Modelling and Their Application to Computer-Assisted Pronunciation Training for Mora-Timed Japanese},
  year = {2023},
  booktitle = {Proceedings of the 4th Kyoto Conference on Arts, Media and Culture}
}

Pyshkin, E., Kusakari, A., Blake, J., & Bogach, N. (2023). Music and Choreography Metaphors in Spoken Language Rhythm Modelling and Their Application to Computer-Assisted Pronunciation Training for Mora-Timed Japanese. In Proceedings of the 4th Kyoto Conference on Arts, Media and Culture.

@inproceedings{lesnichaia2022classification,
  author = {Lesnichaia, M. and Mikhailava, V. and Bogach, N. and Lezhenin, I. and Blake, John and Pyshkin, E.},
  title = {Classification of Accented English Using CNN Model Trained on Amplitude Mel-Spectrograms},
  year = {2022},
  booktitle = {Conference proceedings of Interspeech 2022},
  doi = {10.21437/Interspeech.2022-462}
}

Lesnichaia, M., Mikhailava, V., Bogach, N., Lezhenin, I., Blake, J., & Pyshkin, E. (2022). Classification of Accented English Using CNN Model Trained on Amplitude Mel-Spectrograms. In Conference proceedings of Interspeech 2022. https://doi.org/10.21437/Interspeech.2022-462

@inproceedings{mikhailava2022dynamic,
  author = {Mikhailava, V. and Blake, John and Pyshkin, E. and Bogach, N. and Chernonog, S. and Zhuikov, A. and Lesnichaya, M. and Lezhenin, I. and Svechnikov, R.},
  title = {Dynamic Assessment during Suprasegmental Training with Mobile CAPT},
  year = {2022},
  booktitle = {Conference proceedings of Speech Prosody, 2022},
  pages = {430--434},
  doi = {10.21437/SpeechProsody.2022-88}
}

Mikhailava, V., Blake, J., Pyshkin, E., Bogach, N., Chernonog, S., Zhuikov, A., Lesnichaya, M., Lezhenin, I., & Svechnikov, R. (2022). Dynamic Assessment during Suprasegmental Training with Mobile CAPT. In Conference proceedings of Speech Prosody, 2022 (pp. 430--434). https://doi.org/10.21437/SpeechProsody.2022-88

This paper discusses computer-assisted pronunciation teaching from the perspective of enabling meaningful feedback to learners. We refer to our StudyIntonation project, which is a learning environment that provides feedback on pronunciation exercises to learners based on signal processing algorithms used to construct pitch graphs displayed in a mobile screen, with the support of an audio- visual content repository, and the extensible course developer’s toolkit. Interactive mobile tools aim at providing multimodal tailored feedback according to learner preferences. Such feedback includes evaluative and actionable components. Instructive auditory and visual feedback is tailored using interactive personalized features so that learners can better understand where pronunciation is inappropriate and what to do to improve. The provision of visual speech representation in the form of interactive contours of model and learner’s pitches has a positive effect on learner’s pronunciation of the target language, the latter being an important part of language proficiency. The visual feedback is accomplished by the metrics of the distance between the graphs, based on a dynamic time warping (DTW) algorithm assuring tempo invariant estimation. Though DTW provides an objective primary estimation, we are working on matching the mode and manner of feedback to provide tailored feedback that meets or exceeds learner expectations.

@inproceedings{mikhailava2022tailoring,
  author = {Mikhailava, V. and Pyshkin, E. and Blake, John and Chernonog, S. and Lezhenin, I. and Bogach, N.},
  title = {Tailoring computer-assisted pronunciation teaching: Mixing and matching the mode and manner of feedback to learners},
  year = {2022},
  booktitle = {Proceedings of 16th International Technology, Education and Development Conference (INTED 2022), (pp},
  pages = {767--773},
  doi = {10.21125/inted.2022.0263}
}

Mikhailava, V., Pyshkin, E., Blake, J., Chernonog, S., Lezhenin, I., & Bogach, N. (2022). Tailoring computer-assisted pronunciation teaching: Mixing and matching the mode and manner of feedback to learners. In Proceedings of 16th International Technology, Education and Development Conference (INTED 2022), (pp (pp. 767-773). https://doi.org/10.21125/inted.2022.0263

@inproceedings{nicholas2021identifying,
  author = {Nicholas, A. and Blake, John},
  title = {Identifying and addressing pragmatic failure in a learner corpus of request-based emails},
  year = {2021},
  booktitle = {Proceedings of Japan Association of College English Teachers International Convention 2021, (pp},
  pages = {115--116}
}

Nicholas, A., & Blake, J. (2021). Identifying and addressing pragmatic failure in a learner corpus of request-based emails. In Proceedings of Japan Association of College English Teachers International Convention 2021, (pp (pp. 115-116).

@inproceedings{blake2020generic,
  author = {Blake, John},
  title = {Generic integrity: Visualizing lexicogrammatical features in scientific articles},
  year = {2020},
  booktitle = {proceedings of the British Association of Applied Linguists Annual Conference 2019}
}

Blake, J. (2020). Generic integrity: Visualizing lexicogrammatical features in scientific articles. In proceedings of the British Association of Applied Linguists Annual Conference 2019.

@inproceedings{blake2019capt,
  author = {Blake, John and Bogach, N. and Zhuikov, A. and Lezhenin, I. and Maltcev, M. and Pyshkin, E.},
  title = {CAPT Tool Audio-Visual Feedback Assessment Across a Variety of Learning Styles},
  year = {2019},
  booktitle = {Proceedings of the 2nd Workshop on Information Management in Human-Centric Systems at the 18th IEEE International Conference on Ubiquitous Computing and Communications},
  publisher = {IEEE},
  doi = {10.1109/IUCC/DSCI/SmartCNS.2019.00119}
}

Blake, J., Bogach, N., Zhuikov, A., Lezhenin, I., Maltcev, M., & Pyshkin, E. (2019). CAPT Tool Audio-Visual Feedback Assessment Across a Variety of Learning Styles. In Proceedings of the 2nd Workshop on Information Management in Human-Centric Systems at the 18th IEEE International Conference on Ubiquitous Computing and Communications. IEEE. https://doi.org/10.1109/IUCC/DSCI/SmartCNS.2019.00119

@inproceedings{blake2019visualizing,
  author = {Blake, John},
  title = {Visualizing language patterns to help language learners},
  year = {2019},
  booktitle = {The Language Teacher, 43(6), 19-21. [ pdf ]},
  pages = {19--21}
}

Blake, J. (2019). Visualizing language patterns to help language learners. In The Language Teacher, 43(6), 19-21. [ pdf ] (pp. 19-21).

@inproceedings{pyshkin2019prosody,
  author = {Pyshkin, E. and Blake, John and Lamtev, A. and Lezhenin, I. and Zhuikov, A. and Bogach, N.},
  title = {Prosody Training Mobile Application: Early Design Assessment and Lessons Learned},
  year = {2019},
  booktitle = {Proceedings of 2019 IEEE 10th International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS)},
  publisher = {IEEE},
  doi = {10.1109/IDAACS.2019.8924359}
}

Pyshkin, E., Blake, J., Lamtev, A., Lezhenin, I., Zhuikov, A., & Bogach, N. (2019). Prosody Training Mobile Application: Early Design Assessment and Lessons Learned. In Proceedings of 2019 IEEE 10th International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS). IEEE. https://doi.org/10.1109/IDAACS.2019.8924359

@inproceedings{blake2018grammatical,
  author = {Blake, John and Inoue, J. and Kondo, T.},
  title = {Grammatical error checker for Japanese learners of English},
  year = {2018},
  booktitle = {Proceedings of the 3rd International Conference on Applications in Information Technology},
  doi = {10.1145/3274856.3274885}
}

Blake, J., Inoue, J., & Kondo, T. (2018). Grammatical error checker for Japanese learners of English. In Proceedings of the 3rd International Conference on Applications in Information Technology. https://doi.org/10.1145/3274856.3274885

@inproceedings{blake2018speed-marking,
  author = {Blake, John},
  title = {Speed-Marking: A Case Study},
  year = {2018},
  booktitle = {Proceedings of the International Conference on Innovation in Language Learning}
}

Blake, J. (2018). Speed-Marking: A Case Study. In Proceedings of the International Conference on Innovation in Language Learning.

@inproceedings{kaneko2018english,
  author = {Kaneko, E. and Park, M. and Wilson, I. and Heo, Y. and Roy, D. and Yasuta, T. and Nicholas, A. and Blake, John},
  title = {English Curriculum Innovation for Computer Science Majors in the Japanese EFL Context: From Needs to Tasks},
  year = {2018},
  booktitle = {Proceedings of 2018 IEEE ProComm Annual Conference (pp},
  pages = {84--89},
  publisher = {IEEE},
  doi = {10.1109/ProComm.2018.00028}
}

Kaneko, E., Park, M., Wilson, I., Heo, Y., Roy, D., Yasuta, T., Nicholas, A., & Blake, J. (2018). English Curriculum Innovation for Computer Science Majors in the Japanese EFL Context: From Needs to Tasks. In Proceedings of 2018 IEEE ProComm Annual Conference (pp (pp. 84-89). IEEE. https://doi.org/10.1109/ProComm.2018.00028

@inproceedings{kaneko2018task-based,
  author = {Kaneko, E. and Park, M. and Wilson, I. and Roy, D. and Heo, Y. and Yasuta, T. and Blake, John and Nicholas, A.},
  title = {Task-Based English Curriculum Innovation for Computer Science Majors in Japan: Preliminary Report},
  year = {2018},
  booktitle = {Proceedings of the fourth biennial TBLT in Asia 2018 Conference}
}

Kaneko, E., Park, M., Wilson, I., Roy, D., Heo, Y., Yasuta, T., Blake, J., & Nicholas, A. (2018). Task-Based English Curriculum Innovation for Computer Science Majors in Japan: Preliminary Report. In Proceedings of the fourth biennial TBLT in Asia 2018 Conference. https://www.tblsig.org/publications

@inproceedings{blake2016harnessing,
  author = {Blake, John},
  title = {Harnessing keyness: A corpus-based approach to ESP material development},
  year = {2016},
  booktitle = {OnCUE, 9(2), 102-110. [ pdf ]},
  pages = {102--110}
}

Blake, J. (2016). Harnessing keyness: A corpus-based approach to ESP material development. In OnCUE, 9(2), 102-110. [ pdf ] (pp. 102-110).

@inproceedings{blake2016hidden,
  author = {Blake, John},
  title = {Hidden conversation killers},
  year = {2016},
  booktitle = {English Language Teaching Ideas Journal, 1, 19-24. [ pdf ]},
  pages = {19--24}
}

Blake, J. (2016). Hidden conversation killers. In English Language Teaching Ideas Journal, 1, 19-24. [ pdf ] (pp. 19-24).

@inproceedings{blake2015incorporating,
  author = {Blake, John},
  title = {Incorporating information structure in the EAP curriculum},
  year = {2015},
  booktitle = {Conference proceedings of 2nd International Symposium on Innovative Teaching and Research in ESP, UEC Tokyo}
}

Blake, J. (2015). Incorporating information structure in the EAP curriculum. In Conference proceedings of 2nd International Symposium on Innovative Teaching and Research in ESP, UEC Tokyo.

@inproceedings{blake2015prescriptive-descriptive,
  author = {Blake, John},
  title = {Prescriptive-descriptive disjuncture: Rhetorical organisation of research abstracts in information science},
  year = {2015},
  booktitle = {Conference proceedings in F},
  pages = {377--8}
}

Blake, J. (2015). Prescriptive-descriptive disjuncture: Rhetorical organisation of research abstracts in information science. In Conference proceedings in F (pp. 377-8).

@inproceedings{nguyen2015knowledge,
  author = {Nguyen, L. and Umemoto, K. and Kohda, Y. and Blake, John},
  title = {Knowledge Management in Auditing: A Case Study in Vietnam},
  year = {2015},
  booktitle = {Proceedings of the 16th European Conference on Knowledge Management (ECKM) (pp},
  pages = {571--577}
}

Nguyen, L., Umemoto, K., Kohda, Y., & Blake, J. (2015). Knowledge Management in Auditing: A Case Study in Vietnam. In Proceedings of the 16th European Conference on Knowledge Management (ECKM) (pp (pp. 571-577).

@inproceedings{blake2014responding,
  author = {Blake, John},
  title = {Responding to extended writing electronically},
  year = {2014},
  booktitle = {PeerSpectives, 12, 14-17. [ pdf ]},
  pages = {14--17}
}

Blake, J. (2014). Responding to extended writing electronically. In PeerSpectives, 12, 14-17. [ pdf ] (pp. 14-17).

@inproceedings{blake2014speed-marking,
  author = {Blake, John},
  title = {Speed-marking},
  year = {2014},
  booktitle = {The Language Teacher, 38(4), 51-52. [ http ]},
  pages = {51--52}
}

Blake, J. (2014). Speed-marking. In The Language Teacher, 38(4), 51-52. [ http ] (pp. 51-52). http://jalt-publications.org/tlt/departments/myshare/articles/3855-speed-marking

@inproceedings{hinchey2014from,
  author = {Hinchey, D. and Blake, John and Holden, W.},
  title = {From paper to pixels: The design and delivery of online language courses},
  year = {2014},
  booktitle = {PeerSpectives, 12, 23-25. [ pdf ]},
  pages = {23--25}
}

Hinchey, D., Blake, J., & Holden, W. (2014). From paper to pixels: The design and delivery of online language courses. In PeerSpectives, 12, 23-25. [ pdf ] (pp. 23-25).

@inproceedings{hinchey2014transition,
  author = {Hinchey, D. and Blake, John},
  title = {Transition to tablets},
  year = {2014},
  booktitle = {The Language Teacher, 38(2), 41-43. [ pdf ]},
  pages = {41--43}
}

Hinchey, D., & Blake, J. (2014). Transition to tablets. In The Language Teacher, 38(2), 41-43. [ pdf ] (pp. 41-43).

@inproceedings{blake2013effect,
  author = {Blake, John},
  title = {The effect and affect of reciprocal observation},
  year = {2013},
  booktitle = {Explorations in Teacher Education, 21(3), 3-8. [ pdf ]},
  pages = {3--8}
}

Blake, J. (2013). The effect and affect of reciprocal observation. In Explorations in Teacher Education, 21(3), 3-8. [ pdf ] (pp. 3-8).

@inproceedings{blake2013one,
  author = {Blake, John},
  title = {One class, one improvement: A case study of systematic incremental improvement},
  year = {2013},
  booktitle = {Research on Communication, 11},
  pages = {11}
}

Blake, J. (2013). One class, one improvement: A case study of systematic incremental improvement. In Research on Communication, 11 (pp. 11).

@inproceedings{blake2013review,
  author = {Blake, John and Hinchey, D.},
  title = {Review of 2nd CUE ESP Symposium},
  year = {2013},
  booktitle = {OnCUE, 7(1), 58-62. [ pdf ]},
  pages = {58--62}
}

Blake, J., & Hinchey, D. (2013). Review of 2nd CUE ESP Symposium. In OnCUE, 7(1), 58-62. [ pdf ] (pp. 58-62).

@inproceedings{blake2013statistics,
  author = {Blake, John and Blake, John},
  title = {Statistics for scientists: Incorporating data-driven decision making in the publishing process},
  year = {2013},
  booktitle = {OnCUE, 7(2), 106-109. [ pdf ]},
  pages = {106--109}
}

Blake, J., & Blake, J. (2013). Statistics for scientists: Incorporating data-driven decision making in the publishing process. In OnCUE, 7(2), 106-109. [ pdf ] (pp. 106-109).

@inproceedings{blake2013there,
  author = {Blake, John},
  title = {There are no crocodiles in this hospital},
  year = {2013},
  booktitle = {Medical Education, Volume 46. 10th Asia Pacific Medical Education Conference Handbook}
}

Blake, J. (2013). There are no crocodiles in this hospital. In Medical Education, Volume 46. 10th Asia Pacific Medical Education Conference Handbook.

@inproceedings{blake2012corpus-based,
  author = {Blake, John},
  title = {Corpus-based online common error detector},
  year = {2012},
  booktitle = {Conference proceedings of the 20th International Conference on Computers in Education}
}

Blake, J. (2012). Corpus-based online common error detector. In Conference proceedings of the 20th International Conference on Computers in Education.

@inproceedings{blake2012research,
  author = {Blake, John},
  title = {Research abstract templates: The skeletons are out of the virtual cupboard},
  year = {2012},
  booktitle = {Conference proceedings of the 5th ICT for Language Learning Conference}
}

Blake, J. (2012). Research abstract templates: The skeletons are out of the virtual cupboard. In Conference proceedings of the 5th ICT for Language Learning Conference.

This study presents a multi-objective optimization framework integrating genetic algorithms with deep learning for spacecraft project management, addressing critical challenges in schedule prediction and cost forecasting. The methodology employs binary tournament selection with Pareto dominance ranking, simulated binary crossover (p_c = 0.9, n_c = 20), and CNN-LSTM hybrid architecture for temporal dependency modeling. Comparative analysis across six prediction methods demonstrates superior performance: RMSE of 34.7 days, MAPE of 8.3%, and R² of 0.847, achieving 79.3% accuracy within ±30-day windows and 92.6% within ±60-day windows. The framework attains 94.7% accuracy for baseline expenditure prediction and 73.4% accuracy for unplanned cost growth forecasting, substantially outperforming traditional parametric approaches (25–40% accuracy). These results validate the framework's capability to support data-driven resource allocation, risk-informed budget reserve planning, and proactive stakeholder communication in complex aerospace development programs, enabling more resilient project execution strategies. The framework demonstrates 73.4% accuracy in cost growth prediction compared to traditional 25–40% accuracy, enabling evidence-based decision support for billion-dollar aerospace initiatives.

@incollection{sungheetha2026enhanced,
  author = {Sungheetha, A. and Blake, John and Sharma, R. R. and Yogarayan, S. and Kannan, S.},
  title = {Enhanced AI-Driven Project Management Framework for Complex Space Exploration Missions: A Case Study Analysis of the James Webb Space Telescope},
  year = {2026},
  booktitle = {Proceedings of International Conference on Artificial Intelligence and Networks (ICAIN)},
  pages = {386--395},
  publisher = {Springer Nature Switzerland},
  doi = {10.1007/978-3-032-25617-1_28}
}

Sungheetha, A., Blake, J., Sharma, R., Yogarayan, S., & Kannan, S. (2026). Enhanced AI-Driven Project Management Framework for Complex Space Exploration Missions: A Case Study Analysis of the James Webb Space Telescope. In Proceedings of International Conference on Artificial Intelligence and Networks (ICAIN) (pp. 386-395). Springer Nature Switzerland. https://doi.org/10.1007/978-3-032-25617-1_28

This paper presents an innovative AI-enabled edge computing framework that integrates healthcare monitoring and energy management in smart cities through adaptive binning techniques. The proposed system combines distributed IoT sensors, blockchain-based secure data transmission, and neuromorphic computing to create a scalable infrastructure for urban health monitoring and energy optimization. Our framework addresses critical challenges in existing systems, including data privacy, energy efficiency, and real-time processing capabilities. The SMILE (Secure Middleware for Intelligent Life Enhancement) middleware serves as the core orchestration layer, managing distributed sensor networks while maintaining data security through federated Byzantine fault tolerance mechanisms. Compared to baseline cloud-centric and edge-only architectures, the implementation shows significant improvements in processing efficiency (47% faster than traditional cloud systems), reduction in energy consumption (38% compared to standard edge deployments) and diagnostic accuracy (93.5% versus 85% baseline accuracy). Experimental validation in 14 international deployment sites shows the system's adaptability to diverse urban environments with statistical significance (p<0.001). The framework's integration of adaptive histogram-based stream processing with custom neural networks enables effective management of distributed sensor networks while maintaining data security and system reliability.

@incollection{sungheetha2026bwidth,
  author = {Sungheetha, A. and Sharma, R. R. and Blake, John and Mahapatra, S. and Jeba Singh, O. and Dhawan, A.},
  title = {B_width Adaptive Binning Edge Computing Framework with AI for Smart City Healthcare Monitoring and Energy Management},
  year = {2026},
  booktitle = {Computer Vision and Robotics},
  pages = {43--57},
  publisher = {Springer Nature Switzerland},
  doi = {10.1007/978-3-032-14038-8_4}
}

Sungheetha, A., Sharma, R., Blake, J., Mahapatra, S., Jeba Singh, O., & Dhawan, A. (2026). B_width Adaptive Binning Edge Computing Framework with AI for Smart City Healthcare Monitoring and Energy Management. In Computer Vision and Robotics (pp. 43–57). Springer Nature Switzerland. https://doi.org/10.1007/978-3-032-14038-8_4

This paper presents a novel energy-efficient framework integrating Gallium Nitride (GaN) hardware accelerators with real-time stream processing for sustainable smart city IoT applications. The proposed system combines high-speed modulation characteristics of scaled GaN laser diodes operating at 2.4 GHz with reconfigurable Multiple-In Multiple-Out (MIMO) antenna arrays to enable efficient processing of intensive data streams from urban IoT sensors. The hybrid architecture leverages both edge and cloud computing paradigms, achieving statistically significant improvements of 47.7% in energy efficiency (95% CI: 44.2–51.3%, p<0.001) and 68.0% latency reduction (95% CI: 65.1–70.9%, p<0.001) compared to traditional approaches. The system incorporates resonant-cavity light-emitting diode technology for high-bandwidth data transmission and employs machine learning-based adaptive stream processing algorithms optimized for urban infrastructure monitoring. Experimental validation across 14 international deployments in Singapore, Barcelona, Toronto, and Dubai demonstrates consistent performance improvements while maintaining 99.8% system reliability and processing throughput of 8.7 Gbps.

@incollection{sungheetha2026energy,
  author = {Sungheetha, A. and Sharma, R. R. and Blake, John and Mahapatra, S. and Abeysinghe, N. and Parashar, K.},
  title = {Energy-Efficient GaN-Accelerated Stream Processing Framework for Smart City IoT Applications},
  year = {2026},
  booktitle = {Computer Vision and Robotics},
  pages = {381--394},
  publisher = {Springer Nature Switzerland},
  doi = {10.1007/978-3-032-14038-8_30}
}

Sungheetha, A., Sharma, R., Blake, J., Mahapatra, S., Abeysinghe, N., & Parashar, K. (2026). Energy-Efficient GaN-Accelerated Stream Processing Framework for Smart City IoT Applications. In Computer Vision and Robotics (pp. 381–394). Springer Nature Switzerland. https://doi.org/10.1007/978-3-032-14038-8_30

This paper reports on a Design-Based Research (DBR) study investigating how human–AI interactions can be shaped to approximate the ways human assessors administer dynamic language assessments of pragmatic competence. While conversational AI is increasingly integrated into education, most applications remain text-based and overlook the pedagogical challenges of spoken interaction, particularly in pragmatics. Our project addresses this gap through the iterative design and evaluation of a computerised dynamic language assessment system focused on the speech act of requesting. Across six prototype cycles, users interacted with an AI interlocutor in spoken dialogues while an automated tutor agent monitored interactions for perceived instances of pragmatic inappropriateness and delivered graduated feedback. Analysis of iterative testing revealed distinct patterns in the types of issues encountered: surface-level problems in the graphical user interface (e.g., audio handling, text display, visuals) were relatively easy to resolve, whereas dialogue management, particularly phase disambiguation and parsing, proved more persistent and difficult to automate. These findings suggest that while technical refinements can steadily improve the usability of AI-mediated systems, replicating the subtle interactional and mediation strategies of human interlocutors remains a central challenge. By documenting these refinements, this study demonstrates how DBR can expose the boundary between tractable software improvements, prompt engineering fixes and deeper interactional complexities, providing practical insights for the design of AI-mediated spoken language learning environments.

@incollection{nicholas2026a,
  author = {Nicholas, A. and Blake, John and Mozgovoy, M.},
  title = {A Design-based Research Approach to Developing a Computerised Dynamic Assessment of Oral Pragmatic Competence: Solvable and Persistent Challenges},
  year = {2026},
  publisher = {Springer}
}

Nicholas, A., Blake, J., & Mozgovoy, M. (2026). A Design-based Research Approach to Developing a Computerised Dynamic Assessment of Oral Pragmatic Competence: Solvable and Persistent Challenges. In . Springer.

This paper presents an innovative approach combining triboelectric nanogenerators (TENG) with artificial intelligence for sustainable environmental monitoring. The proposed Adaptive Neural-TENG Integration System (ANTIS) addresses the challenges of power stability and efficiency in environmental sensing applications. By incorporating stream processing analytics through the LARA framework, our system achieves real-time data processing while optimizing energy harvesting efficiency. The methodology integrates neuromorphic computing principles with TENG-based power generation, achieving a 47% improvement in energy harvesting efficiency compared to conventional methods. Experimental results across 14 countries demonstrate the system's adaptability to various environmental conditions, with an average response time of 3.2ms and 92% accuracy in environmental parameter detection. This research contributes to the development of self-powered, intelligent environmental monitoring systems with potential applications in smart cities and precision agriculture.

@incollection{sungheetha2026ai-driven,
  author = {Sungheetha, A. and Blake, John and Sharma, R. R. and Mahapatra, S. and Jeba Singh, O.},
  title = {AI-Driven Sustainable Energy Harvesting System with Triboelectric Nanogenerators for Smart Environmental Monitoring},
  year = {2026},
  booktitle = {Proceedings of Fifth International Conference on Computing and Communication Networks},
  pages = {431--441},
  publisher = {Springer Nature Switzerland},
  doi = {10.1007/978-3-032-18910-3_39}
}

Sungheetha, A., Blake, J., Sharma, R., Mahapatra, S., & Jeba Singh, O. (2026). AI-Driven Sustainable Energy Harvesting System with Triboelectric Nanogenerators for Smart Environmental Monitoring. In Proceedings of Fifth International Conference on Computing and Communication Networks (pp. 431–441). Springer Nature Switzerland. https://doi.org/10.1007/978-3-032-18910-3_39

Here we report on the development of the first Computerized Dynamic Assessment (C-DA) platform for pragmatic failure in request emails written by Japanese learners of English. Dynamic language assessments are usually dyadic interactions between the tutor and the learner. In our online C-DA, we harness natural language processing algorithms to detect specific instances of pragmatic failure in learner email texts. On matching, graduated feedback in the form of increasingly more explicit hints is displayed sequentially until either learners have appropriately revised the text or the allocated number of attempts is reached. The C-DA incorporates researcher- and learner-facing interfaces, automatically generates progress reports for learners, and tracks all activities for research purposes.

@incollection{blake2025computerized,
  author = {Blake, John and Mozgovoy, M. and Nicholas, A.},
  title = {Computerized Dynamic Assessment for pragmatic competence in second language learners' English email requests},
  year = {2025},
  booktitle = {Methodologies and Intelligent Systems for Technology Enhanced Learning Workshops -- 14th International Conference},
  pages = {17--28},
  publisher = {Springer},
  doi = {10.1007/978-3-031-85561-0_2}
}

Blake, J., Mozgovoy, M., & Nicholas, A. (2025). Computerized Dynamic Assessment for pragmatic competence in second language learners' English email requests. In Methodologies and Intelligent Systems for Technology Enhanced Learning Workshops -- 14th International Conference (pp. 17–28). Springer. https://doi.org/10.1007/978-3-031-85561-0_2

This chapter investigates the interplay between ethical considerations and artificial intelligence (AI) in content production and interpretation by transcultural audiences, focusing on integrity, inclusivity, and impact. It argues for the enhancement of critical and digital literacy to assess the authenticity of AI-mediated narratives, the need for AI to support rather than replace human judgment in avoiding misinformation, and the development of human-centric AI systems that respect cultural subtleties and foster equitable representation. Through ethical frameworks, such as consequentialism, deontological ethics, virtue ethics, and the ethics of care, I advocate for AI that promotes truthfulness, mitigates biases, and respects diverse identities. Transparency and critical literacy are paramount in empowering audiences to demand diverse media narratives and the responsibility for ensuring AI-generated content does not perpetuate stereotypes is placed on both the users and creators of AI. This chapter calls for ethical AI deployment that aligns with human values and enhances global cultural discourse, showing the significance of ethical foresight and humanistic considerations in transcultural communications.

@incollection{blake2025ethics,
  author = {Blake, John},
  title = {The Ethics of AI in media: Crafting integrity, inclusivity, and impact},
  year = {2025},
  booktitle = {Transcultural Media Narratives: Cross-cultural Communication Insights},
  editor = {Camilo, E. and Bouziane, K.},
  pages = {229--254},
  publisher = {Labcom Publications}
}

Blake, J. (2025). The Ethics of AI in media: Crafting integrity, inclusivity, and impact. In E. Camilo & K. Bouziane (Eds.), Transcultural Media Narratives: Cross-cultural Communication Insights (pp. 229-254). Labcom Publications. https://labcom.ubi.pt/transcultural-media-narratives-cross-cultural-communication-insights/

This paper explores the transformative impact of LLMs on education and proposes an innovative solution: harnessing bimodal input and output as a means to boost, not bypass, the learning process. This proposed approach emphasizes the critical roles of synthesis and analysis within learning tasks. By structuring assignments in a manner that requires students to synthesize information from different sources to create suitable prompts for LLMs, the true potential of learning is reignited. Furthermore, students need to analyze the output of the LLM to create the required mode and format. This process necessitates a higher level of cognitive engagement, fostering critical thinking, creativity, and active learning. By interweaving textual and non-textual elements, the bimodal approach ensures that students are not merely recipients of information but active constructors of knowledge. By embracing the bimodal approach, the potential hindrance of LLMs is transformed into a powerful tool enriching and amplifying the learning process.

@incollection{blake2025learning,
  author = {Blake, John},
  title = {Learning in the age of LLMs: Boosting not bypassing the learning process},
  year = {2025},
  booktitle = {Transcending Boundaries in the Digital Age, Educational Communications and Technology Yearbook},
  editor = {S.K.K. Ng et al.},
  publisher = {Springer},
  doi = {10.1007/978-981-96-2921-3_9}
}

Blake, J. (2025). Learning in the age of LLMs: Boosting not bypassing the learning process. In S.K.K. Ng et al. (Ed.), Transcending Boundaries in the Digital Age, Educational Communications and Technology Yearbook. Springer. https://doi.org/10.1007/978-981-96-2921-3_9

Time series descriptions often accompany graphs to help readers focus on the key trends. Major English language proficiency tests, such as IELTS and TOEIC, incorporate such descriptions into their written examinations. Trend descriptions are, therefore, a high-stakes genre for learners of English aiming to study at universities in Anglophone countries. To help learners become more familiar with the genre and to provide language practice at an appropriate level, we developed TrendScribe. This is the first interactive online tool that enables users to generate textual descriptions of single-line graphs from user-submitted time series data. Both rule-based and LLM-based systems are used to generate textual descriptions. Complex datasets are preprocessed using a smoothing algorithm. Users can view descriptions at their preferred proficiency level, with each level offering a corresponding increase in lexical and grammatical complexity.

@incollection{blake2025trendscribe,
  author = {Blake, John and Zhao, Peng and Pyshkin, Evgeny},
  title = {TrendScribe: Design and Development of a Pedagogic Trend Description Generator for Learners of English},
  year = {2025},
  booktitle = {Proceedings of the 17th International Conference on Multi-disciplinary Trends in Artificial Intelligent, Springer Lecture Notes in Artificial Intlligence},
  editor = {C. Sombattheera, Weng, P. and Pang, J.},
  pages = {89--101},
  publisher = {Springer},
  doi = {10.1007/978-981-96-0692-4_8}
}

Blake, J., Zhao, P., & Pyshkin, E. (2025). TrendScribe: Design and Development of a Pedagogic Trend Description Generator for Learners of English. In Weng C. Sombattheera & J. Pang (Eds.), Proceedings of the 17th International Conference on Multi-disciplinary Trends in Artificial Intelligent, Springer Lecture Notes in Artificial Intlligence (pp. 89-101). Springer. https://doi.org/10.1007/978-981-96-0692-4_8

@incollection{pyshkin2024dispelling,
  author = {Pyshkin, E. and Blake, John},
  title = {Dispelling the seven myths of Tchaikovsky's Children's Album through computational and language modeling},
  year = {2024},
  editor = {E. Himonides, Johnson, C., Prior, H., and King, A.},
  pages = {29--31},
  doi = {10.17605/OSF.IO/WE2AV}
}

Pyshkin, E., & Blake, J. (2024). Dispelling the seven myths of Tchaikovsky's Children's Album through computational and language modeling. In Johnson E. Himonides & A. King (Eds.), (pp. 29-31). https://doi.org/10.17605/OSF.IO/WE2AV

With the burgeoning growth of the metaverse and online virtual environments, new security challenges have been introduced that require careful exploration and mitigation. An increasing proportion of human interactions and transactions now take place in these digital spaces, making it essential to protect users and ensure the safety and integrity of virtual worlds. This chapter explores three dimensions of this issue. First, through a study of the types of crimes that occur in these environments, to gain a holistic under- standing of the cybercrime technoscape. Second, the authors use a two-pronged approach to increase the safety of the metaverse by targeting both potential perpetrators and victims. This is achievable by identifying indicators that may be used to detect potential perpetrators or victims. Thirdly and finally, strategies and techniques to make these online communities safer are suggested.

@incollection{blake2023blake,
  author = {Blake, John and In Elshenraki, H.},
  title = {Blake, J},
  year = {2023},
  editor = {the Metaverse: A Study on Classification, Prediction, and Mitigation Strategies. In Elshenraki, H.},
  pages = {66--77},
  publisher = {IGI Global},
  doi = {10.4018/979-8-3693-0220-0.ch004}
}

Blake, J., & In Elshenraki, H. (2023). Blake, J. In Prediction the Metaverse: A Study on Classification & H. Mitigation Strategies. In Elshenraki (Eds.), (pp. 66-77). IGI Global. https://doi.org/10.4018/979-8-3693-0220-0.ch004

@incollection{blake2023intelligent,
  author = {Blake, John},
  title = {Intelligent CALL: Individualizing learning using natural language generation},
  year = {2023},
  editor = {A.W.B. Tso, Ng, S.K.K., Law, L., and Bai, T.S.},
  pages = {3--18},
  publisher = {Springer},
  doi = {10.1007/978-981-19-9217-9_1}
}

Blake, J. (2023). Intelligent CALL: Individualizing learning using natural language generation. In Ng A.W.B. Tso & T.S. Bai (Eds.), (pp. 3-18). Springer. https://doi.org/10.1007/978-981-19-9217-9_1

Generative artificial intelligence, anchored by large language models (LLMs), is significantly altering the educational landscape. This chapter examines the impact of generative AI on education, illustrating its capability to create personalized content and transform learning environments. Despite concerns over academic dishonesty facilitated by LLMs, the chapter argues against a regressive stance and advocates for the constructive integration of AI into educational practices. By drawing on theories of learning, the chapter elucidates the pedagogical implications of generative AI and describes specific use cases in language learning, computer science, and mathematics. Highlighting both the potential and limitations of this emerging technology, the chapter posits that generative AI is not merely a disruptive force, but a revolutionary tool poised to redefine the methodologies of teaching and learning.

@incollection{blake2023unleashing,
  author = {Blake, John},
  title = {Unleashing the potential: Positive impacts of generative AI on learning and teaching},
  year = {2023},
  editor = {Hai-Jew, S.},
  publisher = {IGI Global},
  doi = {10.4018/979-8-3693-0074-9.ch002}
}

Blake, J. (2023). Unleashing the potential: Positive impacts of generative AI on learning and teaching. In S. Hai-Jew (Ed.), . IGI Global. https://doi.org/10.4018/979-8-3693-0074-9.ch002

@incollection{khaustova2023capturing,
  author = {Khaustova, V. and Pyshkin, E. and Khaustov, V. and Blake, John and Bogach, N.},
  title = {CAPTuring Accents: An Approach to Personalize Pronunciation Training for Learners with Different L1 Backgrounds},
  year = {2023},
  publisher = {Springer},
  doi = {10.1007/978-3-031-48312-7_5}
}

Khaustova, V., Pyshkin, E., Khaustov, V., Blake, J., & Bogach, N. (2023). CAPTuring Accents: An Approach to Personalize Pronunciation Training for Learners with Different L1 Backgrounds. In . Springer. https://doi.org/10.1007/978-3-031-48312-7_5

@incollection{holden2022development,
  author = {Holden, W. and Blake, John},
  title = {Development of an English for Research Purposes Program for STEM Graduate Students},
  year = {2022},
  editor = {G. Hill, Falout, J. and Apple, M.},
  publisher = {Palgrave McMillan},
  doi = {10.1007/978-3-031-11116-7_5}
}

Holden, W., & Blake, J. (2022). Development of an English for Research Purposes Program for STEM Graduate Students. In Falout G. Hill & M. Apple (Eds.), . Palgrave McMillan. https://doi.org/10.1007/978-3-031-11116-7_5

@incollection{pyshkin2022bringing,
  author = {Pyshkin, E. and Blake, John},
  title = {Bringing linguistics to a programming class: A problem of automatic text generation for describing data series},
  year = {2022},
  editor = {H. Fujita, Y. Watanobe, and T. Azumi},
  pages = {621--630},
  publisher = {IOS Press},
  doi = {10.3233/FAIA220291}
}

Pyshkin, E., & Blake, J. (2022). Bringing linguistics to a programming class: A problem of automatic text generation for describing data series. In Y. Watanobe H. Fujita & T. Azumi (Eds.), (pp. 621-630). IOS Press. https://doi.org/10.3233/FAIA220291

@incollection{blake2021empowering,
  author = {Blake, John and Holden, W.},
  title = {Empowering and engaging scientific writers across disciplines},
  year = {2021},
  editor = {B. Morrison, J. Chen, L. Lin and A. Urmston},
  pages = {73--89},
  publisher = {WAC Clearinghouse},
  doi = {10.37514/INT-B.2021.1220.2.04}
}

Blake, J., & Holden, W. (2021). Empowering and engaging scientific writers across disciplines. In J. Chen B. Morrison & A. Urmston (Eds.), (pp. 73-89). WAC Clearinghouse. https://doi.org/10.37514/INT-B.2021.1220.2.04

Error-free scientific research articles are more likely to be accepted for publication than those permeated with errors. This chapter identifies, describes, and explains how to avoid 22 common language errors. Scientists need to master the genre of scientific writing to conform to the generic expectations of the community of practice. Based on a systematic analysis of the pedagogic literature, five categories of errors were identified in scientific research articles namely accuracy, brevity, clarity, objectivity, and formality. To gain a more in-depth understanding of the errors, a corpus investigation of scientific articles was conducted. A corpus of 200 draft research articles submitted for internal review at a research institute with university status was compiled, annotated, and analyzed. This investigation showed empirically the types of errors within these categories that may impinge on publication success. In total, 22 specific types of language errors were identified. These errors are explained, and ways for overcoming each of them are described.

@incollection{blake2021scientific,
  author = {Blake, John},
  title = {Scientific research articles: Twenty-two language errors to avoid},
  year = {2021},
  booktitle = {Improving Scientific Communication for Lifelong Learners,},
  editor = {G. Kurubacak-Meric and S. Sisman-Ugur},
  pages = {195--219},
  publisher = {IGI Global}
}

Blake, J. (2021). Scientific research articles: Twenty-two language errors to avoid. In G. Kurubacak-Meric & S. Sisman-Ugur (Eds.), Improving Scientific Communication for Lifelong Learners, (pp. 195-219). IGI Global. https://www.igi-global.com/book/improving-scientific-communication-lifelong-learners/244489

@incollection{nicholas2021efl,
  author = {Nicholas, A. and Blake, John and Mozgovoy, M.},
  title = {EFL learners and English email writing: Developing a computerised diagnostic language assessment},
  year = {2021},
  editor = {N. Zoghlami, C. Brudermann, C. Sarré, M. Grosbois, L. Bradley, and S. Thouësny},
  pages = {238--242},
  publisher = {Research-publishing.net}
}

Nicholas, A., Blake, J., & Mozgovoy, M. (2021). EFL learners and English email writing: Developing a computerised diagnostic language assessment. In C. Brudermann N. Zoghlami & S. Thouësny (Eds.), (pp. 238-242). Research-publishing.net. https://research-publishing.net/manuscript?10.14705/rpnet.2021.54.1339

@incollection{tranvu2021design,
  author = {Tran Vu, D. and Blake, John},
  title = {Design and development of a question generator for learners of English},
  year = {2021},
  editor = {D. Roy, G. Fragulis and H.A. Cantu Campos},
  pages = {01011},
  doi = {10.1051/shsconf/202110201011}
}

Tran Vu, D., & Blake, J. (2021). Design and development of a question generator for learners of English. In G. Fragulis D. Roy & H.A. Cantu Campos (Eds.), (pp. 01011). https://doi.org/10.1051/shsconf/202110201011

@incollection{blake2020applied,
  author = {Blake, John},
  title = {Applied logic: A mastery learning approach delivered fully online},
  year = {2020},
  editor = {So, H. J., Rodrigo, M.M., Mason, J. and Mitrovic, A.},
  pages = {261--268},
  publisher = {Asia-Pacific Society}
}

Blake, J. (2020). Applied logic: A mastery learning approach delivered fully online. In H. J. So & A. Mitrovic (Eds.), (pp. 261-268). Asia-Pacific Society.

@incollection{blake2020automatic,
  author = {Blake, John},
  title = {Automatic identification of tense and grammatical meaning in context},
  year = {2020},
  editor = {So, H. J., Rodrigo, M.M., Mason, J. and Mitrovic, A.},
  pages = {739--742},
  publisher = {Asia-Pacific Society}
}

Blake, J. (2020). Automatic identification of tense and grammatical meaning in context. In H. J. So & A. Mitrovic (Eds.), (pp. 739-742). Asia-Pacific Society.

@incollection{blake2020development,
  author = {Blake, John},
  title = {Development of online tense and aspect identifier for English},
  year = {2020},
  editor = {K.-M. Frederiksen, S.Larsen, L.Bradley, and S. Thouësny},
  pages = {1--6},
  doi = {10.14705/rpnet.2020.48.1161}
}

Blake, J. (2020). Development of online tense and aspect identifier for English. In S.Larsen K.-M. Frederiksen & S. Thouësny (Eds.), (pp. 1-6). https://doi.org/10.14705/rpnet.2020.48.1161

This chapter shows readers the importance and application of pattern matching in learning languages; specifically, the application of natural language processing to address specific problems of Japanese learners of English at a public university. The chapter introduces the concepts of patterns, detection, and detection methods. The author turns to the pedagogic application of pattern matching, first discussing the relevant theory, then describing hacks developed by language teachers and learners. The final sec- tion describes and evaluates iCALL tools developed at the University of Aizu, including a mobile app and the Pronunciation Scaffolder, a real-time presentation script annotator.

@incollection{blake2020intelligent,
  author = {Blake, John},
  title = {Intelligent CALL: Using pattern matching to learn English},
  year = {2020},
  booktitle = {New Technological Applications for Foreign and Second Language Learning and Teaching,},
  editor = {Mariusz Kruk and Mark Peterson},
  pages = {1--23},
  publisher = {IGI Global}
}

Blake, J. (2020). Intelligent CALL: Using pattern matching to learn English. In Mariusz Kruk & Mark Peterson (Eds.), New Technological Applications for Foreign and Second Language Learning and Teaching, (pp. 1-23). IGI Global. https://www.igi-global.com/book/new-technological-applications-foreign-second/237011

The abstract is published online only. If you did not include a short abstract for the online version when you submitted the manuscript, the first paragraph or the first 10 lines of the chapter will be displayed here. If possible, please provide us with an informative abstract. Students who triumph at school may flunk in the workplace. Undergraduates who excel at university do not necessarily excel at work, and vice versa. In a opinion survey of 400 employers in the US, the majority felt that recent college graduates were ill-prepared for the workplace. Researchers have also pointed out that university graduates have difficulty applying the skills learnt in higher education settings in real-world situations.

@incollection{blake2020real-world,
  author = {Blake, John},
  title = {Real-world simulation: Software development},
  year = {2020},
  editor = {C. Ma and W.W.K. Ma},
  pages = {303--317},
  publisher = {Springer Nature},
  doi = {10.1007/978-981-15-3142-2_23}
}

Blake, J. (2020). Real-world simulation: Software development. In C. Ma & W.W.K. Ma (Eds.), (pp. 303-317). Springer Nature. https://doi.org/10.1007/978-981-15-3142-2_23

@incollection{nicholas2020annotating,
  author = {Nicholas, A. and Blake, John},
  title = {Annotating pragmatic errors in a Japanese learner corpus of English emails},
  year = {2020},
  booktitle = {Learner Corpus Studies in Asia and the World},
  editor = {S. Ishikawa},
  pages = {94--109}
}

Nicholas, A., & Blake, J. (2020). Annotating pragmatic errors in a Japanese learner corpus of English emails. In S. Ishikawa (Ed.), Learner Corpus Studies in Asia and the World (pp. 94-109). http://www.lib.kobe-u.ac.jp/kernel/seika/ISSN=21876746.html

@incollection{nicholas2020a,
  author = {Nicholas, A. and Blake, John},
  title = {A failure mode and effects analysis of pragmatic errors in learner e-mails},
  year = {2020},
  booktitle = {SHS Web Conf, Volume 77},
  editor = {D. Roy},
  pages = {1--6},
  publisher = {ACM},
  doi = {10.1051/shsconf/20207702001}
}

Nicholas, A., & Blake, J. (2020). A failure mode and effects analysis of pragmatic errors in learner e-mails. In D. Roy (Ed.), SHS Web Conf, Volume 77 (pp. 1-6). ACM. https://doi.org/10.1051/shsconf/20207702001

@incollection{blake2019annotated,
  author = {Blake, John},
  title = {Annotated scientific text visualizer: Design, development and deployment},
  year = {2019},
  editor = {Fanny Meunier, Julie Van de Vyver, Linda Bradley, and Sylvie Thouësny},
  pages = {45--50},
  doi = {10.14705/rpnet.2019.38.984}
}

Blake, J. (2019). Annotated scientific text visualizer: Design, development and deployment. In Julie Van de Vyver Fanny Meunier & Sylvie Thouësny (Eds.), (pp. 45-50). https://doi.org/10.14705/rpnet.2019.38.984

@incollection{blake2019argument,
  author = {Blake, John},
  title = {Argument Analyzer: Visualizing and explaining logical arguments in context},
  year = {2019},
  editor = {Chang, M., So, H.J., Wong, L.H., Shih, J.L. and Yu, F.Y.},
  pages = {308--313},
  publisher = {Asia-Pacific Society}
}

Blake, J. (2019). Argument Analyzer: Visualizing and explaining logical arguments in context. In M. Chang & F.Y. Yu (Eds.), (pp. 308-313). Asia-Pacific Society.

@incollection{nicholas2019diagnostic,
  author = {Nicholas, A. and Blake, John},
  title = {Diagnostic Language Assessment: Lessons Learned from Rapid Prototyping},
  year = {2019},
  editor = {Chang, M., So, H.J., Wong, L.H., Shih, J.L. and Yu, F.Y.},
  pages = {679--684},
  publisher = {Asia-Pacific Society}
}

Nicholas, A., & Blake, J. (2019). Diagnostic Language Assessment: Lessons Learned from Rapid Prototyping. In M. Chang & F.Y. Yu (Eds.), (pp. 679-684). Asia-Pacific Society.

This study describes the design and development of a corpus-based error detector for short research articles produced by computer science majors. This genre-specific error detector provides automated pedagogic feedback on surface-level errors using rule-based pattern matching. In the corpus phase, a learner corpus of all theses (n = 629) submitted for three academic years was compiled. A held- out corpus of 50 theses was created for evaluation purposes. The remaining theses were added to the working corpus. Errors in the working corpus were identified manually and automatically. The first 50 theses were annotated using the UAM Corpus Tool. Errors were classified into one of five categories (i.e. accuracy, brevity, clarity, objectivity and formality). By the fiftieth thesis, saturation had been reached, that is the number of new errors discovered had dropped considerably. Annotated errors were extracted into an error bank (xml file). Each error was assigned values for severity, detectability and frequency. The weighted priority of each error was calculated from these values. For the remaining theses only new errors were recorded and were added directly into the error bank. In the software phase, regular expressions were created. Easy-to-understand actionable advice was written that could be displayed on matching the error.

@incollection{blake2018corpus-based,
  author = {Blake, John},
  title = {Corpus-based error detector for Computer Science},
  year = {2018},
  editor = {Y. Tono and Isahara, H.},
  pages = {50--54}
}

Blake, J. (2018). Corpus-based error detector for Computer Science. In Y. Tono & H. Isahara (Eds.), (pp. 50-54).

Through an extended case study, this paper reveals the metaphorical skeletons hidden in statistical cupboards of selective reporting, casting a new light on inter-annotator agreement (IAA) measures. Strategic decisions and their impacts on IAA were tracked in an extended corpus study of rhetorical functions in scientific research abstracts. A search of the research notes of the principal investigator resulted in 142 notes tagged with #IAA that were written between 2013 and 2017. The strategic decisions and their actual or perceived impacts on IAA were logged. A root cause analysis was also conducted to identify the causal factors that reduce IAA. The results show numerous strategic decisions, which using template analysis, were grouped into three categories, namely methodological, statistical and rhetorical. High IAA may be attributed to sound or cogent methodological choices, but it could also be due to manipulating the statistical smoke and rhetorical mirrors. With no standardized convention for reporting IAA in corpus linguistics, researchers can select statistics that portray IAA more or less positively. The metaphorical skeletons hidden in statistical cupboards of selective reporting are revealed, casting a new light on IAA measures of agreement and disagreement. Practical guidelines on best practice are suggested.

@incollection{blake2018inter-annotator,
  author = {Blake, John},
  title = {Inter-annotator Agreement: By hook or by crook},
  year = {2018},
  editor = {Y. Tono and Isahara, H.},
  pages = {43--49}
}

Blake, J. (2018). Inter-annotator Agreement: By hook or by crook. In Y. Tono & H. Isahara (Eds.), (pp. 43-49).

@incollection{blake2018learning,
  author = {Blake, John},
  title = {Learning through induced errors: A garden-path approach to introductory statistics},
  year = {2018},
  editor = {M.A. Sorto, A. White, and L. Guyot}
}

Blake, J. (2018). Learning through induced errors: A garden-path approach to introductory statistics. In A. White M.A. Sorto & L. Guyot (Eds.), .

@book{roy2020pansig,
  author = {Roy, D. and Blake, John},
  title = {PanSIG Journal 2019},
  year = {2020},
  publisher = {JALT}
}

Roy, D., & Blake, J. (2020). PanSIG Journal 2019. JALT.

@book{roy2019pansig,
  author = {Roy, D. and Blake, John},
  title = {PanSIG Journal 2018},
  year = {2019},
  publisher = {JALT}
}

Roy, D., & Blake, J. (2019). PanSIG Journal 2018. JALT.

@book{lai2004daily,
  author = {Lai, V. and Blake, John and Cheung, M.},
  title = {Daily Life in Hong Kong},
  year = {2004},
  publisher = {Ming Pao Publishing}
}

Lai, V., Blake, J., & Cheung, M. (2004). Daily Life in Hong Kong. Ming Pao Publishing.

@book{lai2004get,
  author = {Lai, V. and Blake, John and Cheung, M.},
  title = {Get a Job and Succeed},
  year = {2004},
  publisher = {Ming Pao Publishing}
}

Lai, V., Blake, J., & Cheung, M. (2004). Get a Job and Succeed. Ming Pao Publishing.

@misc{blake2022describing,
  author = {Blake, John},
  title = {Describing trends: Individualizing practice using natural language generation},
  year = {2022},
  howpublished = {Language for Specific Purposes and Professional Communication (LSPPC) Newsletter, 4, 13-16},
  url = {https://www.lsppc.org/archives}
}

Blake, J. (2022). Describing trends: Individualizing practice using natural language generation. Language for Specific Purposes and Professional Communication (LSPPC) Newsletter, 4, 13-16. https://www.lsppc.org/archives

@misc{villegas2022typesetting,
  author = {Villegas, J. and Blake, John},
  title = {Typesetting instructions},
  year = {2022},
  howpublished = {Online Resource of University of Aizu},
  url = {https://onkyo.u-aizu.ac.jp/typesetting/}
}

Villegas, J., & Blake, J. (2022). Typesetting instructions. Online Resource of University of Aizu. https://onkyo.u-aizu.ac.jp/typesetting/

@misc{blake2021corpus-based,
  author = {Blake, John},
  title = {Corpus-based study of the rhetorical organization and lexical realization of scientific research abstracts},
  year = {2021},
  howpublished = {Aston University [Doctoral Dissertation]},
  url = {https://research.aston.ac.uk/en/studentTheses/corpus-based-study-of-the-rhetorical-organization-and-lexical-rea}
}

Blake, J. (2021). Corpus-based study of the rhetorical organization and lexical realization of scientific research abstracts. Aston University [Doctoral Dissertation]. https://research.aston.ac.uk/en/studentTheses/corpus-based-study-of-the-rhetorical-organization-and-lexical-rea

@misc{blake2021transition,
  author = {Blake, John},
  title = {Transition from textbook to digital delivery},
  year = {2021},
  howpublished = {Abstracts of the 17th Asia Association of Computer Assisted Language Learning International Conference and VLTESOL},
  url = {https://asiacall.info/acoj/index.php/journal/article/view/46/15}
}

Blake, J. (2021). Transition from textbook to digital delivery. Abstracts of the 17th Asia Association of Computer Assisted Language Learning International Conference and VLTESOL. https://asiacall.info/acoj/index.php/journal/article/view/46/15

@misc{blake2020english,
  author = {Blake, John},
  title = {English Verb Analyzer: Identifying tense, voice, aspect, sense and grammatical meaning in context for pedagogic purposes},
  year = {2020},
  howpublished = {Extended abstract in 8th Swedish Language Technology Conference 2020 program},
  url = {https://gubox.app.box.com/v/SLTC-2020-paper-25}
}

Blake, J. (2020). English Verb Analyzer: Identifying tense, voice, aspect, sense and grammatical meaning in context for pedagogic purposes. Extended abstract in 8th Swedish Language Technology Conference 2020 program. https://gubox.app.box.com/v/SLTC-2020-paper-25

@misc{blake2019pronunciation,
  author = {Blake, John},
  title = {Pronunciation Scaffolder},
  year = {2019},
  howpublished = {The Word, 29(1), 17-18}
}

Blake, J. (2019). Pronunciation Scaffolder. The Word, 29(1), 17-18.

@misc{blake2018sound,
  author = {Blake, John},
  title = {Sound start, firm finish},
  year = {2018},
  howpublished = {English Teaching Professional, 116}
}

Blake, J. (2018). Sound start, firm finish. English Teaching Professional, 116.

@misc{kondo2018pronunciation,
  author = {Kondo, T. and Inoue, J. and Blake, John},
  title = {Pronunciation Scaffolder: Annotation accuracy},
  year = {2018},
  howpublished = {Extended abstract in Conference booklet of 2nd International Symposium on Applied Phonetics}
}

Kondo, T., Inoue, J., & Blake, J. (2018). Pronunciation Scaffolder: Annotation accuracy. Extended abstract in Conference booklet of 2nd International Symposium on Applied Phonetics.

@misc{blake2012harnessing,
  author = {Blake, John},
  title = {Harnessing technology to help researchers avoid plagiarism},
  year = {2012},
  howpublished = {Extended abstract in KOTESOL International Conference 2012 handbook}
}

Blake, J. (2012). Harnessing technology to help researchers avoid plagiarism. Extended abstract in KOTESOL International Conference 2012 handbook.

@misc{blake2012scientific,
  author = {Blake, John and Hinchey, D.},
  title = {Scientific abstracts vs. simplified readers: Investigating the effect on affect},
  year = {2012},
  howpublished = {Extended abstract in KOTESOL International Conference 2012 handbook}
}

Blake, J., & Hinchey, D. (2012). Scientific abstracts vs. simplified readers: Investigating the effect on affect. Extended abstract in KOTESOL International Conference 2012 handbook.

@misc{blake2012understanding,
  author = {Blake, John},
  title = {Understanding samurai dramas: An investigation into scaffolding students of Japanese through the cultural and linguistic entry barriers},
  year = {2012},
  howpublished = {Working papers of the 4th North East Asian Region Language Education Conference}
}

Blake, J. (2012). Understanding samurai dramas: An investigation into scaffolding students of Japanese through the cultural and linguistic entry barriers. Working papers of the 4th North East Asian Region Language Education Conference.

@misc{lai2004english,
  author = {Lai, V. and Blake, John and Cheung, M.},
  title = {English everywhere},
  year = {2004},
  howpublished = {Newspaper column}
}

Lai, V., Blake, J., & Cheung, M. (2004). English everywhere. Newspaper column.

@misc{lai2003english,
  author = {Lai, V. and Blake, John and Cheung, M.},
  title = {English everywhere},
  year = {2003},
  howpublished = {Newspaper column}
}

Lai, V., Blake, J., & Cheung, M. (2003). English everywhere. Newspaper column.

@misc{lai2002english,
  author = {Lai, V. and Blake, John and Cheung, M.},
  title = {English everywhere},
  year = {2002},
  howpublished = {Newspaper column}
}

Lai, V., Blake, J., & Cheung, M. (2002). English everywhere. Newspaper column.

@article{author2026evaluating,
  author = {Author, A. and Author, A. and Blake, John and Authors, More},
  title = {Evaluating Native and Foreign Language Practice with an Embodied Virtual Agent through Biosignal Analysis},
  year = {2026}
}

Author, A., Author, A., Blake, J., & Authors, M. (2026). Evaluating Native and Foreign Language Practice with an Embodied Virtual Agent through Biosignal Analysis. .

@inproceedings{author2026genre,
  author = {Author, A. and Blake, John and Author, A. and Author, A.},
  title = {Genre-Residualized Authorship Attribution Model: Mitigating Cross-Genre Effects under Data Scarcity},
  year = {2026}
}

Author, A., Blake, J., Author, A., & Author, A. (2026). Genre-Residualized Authorship Attribution Model: Mitigating Cross-Genre Effects under Data Scarcity. In .

@inproceedings{author2026grounded-theory-inspired,
  author = {Author, An and Blake, John and Author, Another},
  title = {Grounded-Theory-Inspired Human-Led Agentic Pipeline for Qualitative Analysis: A Proof-of-Concept},
  year = {2026},
  booktitle = {18th International Conference on Human System Interaction}
}

Author, A., Blake, J., & Author, A. (2026). Grounded-Theory-Inspired Human-Led Agentic Pipeline for Qualitative Analysis: A Proof-of-Concept. In 18th International Conference on Human System Interaction.

@article{author2026an,
  author = {Author, An and Blake, John and Author, Another},
  title = {An Extensible Framework for Interactive Pronunciation Support for Orthographically Complex Languages: The Case of Sinhala},
  year = {2026},
  journal = {journal}
}

Author, A., Blake, J., & Author, A. (2026). An Extensible Framework for Interactive Pronunciation Support for Orthographically Complex Languages: The Case of Sinhala. journal.

@inproceedings{author2026human-verifiable,
  author = {Author, An and Blake, John and Another, Another},
  title = {Human-Verifiable API Documentation Generation for Legacy Web Frameworks Using Multi-Agent LLMs},
  year = {2026}
}

Author, A., Blake, J., & Another, A. (2026). Human-Verifiable API Documentation Generation for Legacy Web Frameworks Using Multi-Agent LLMs. In undefined.

@article{blake2026a,
  author = {Blake, John and Author, An},
  title = {A rule-based algorithm for identifying request head acts in L2 English learner emails},
  year = {2026}
}

Blake, J., & Author, A. (2026). A rule-based algorithm for identifying request head acts in L2 English learner emails. undefined.

Automated API documentation and test generation for Python web applications remain challenging due to the fragmentation of the framework ecosystem and the limitations of existing single-framework tools. We present a framework-adaptive multi-agent pipeline supporting seven Python web frameworks — Django, FastAPI, Flask, Bottle, Tornado, Pyramid, and Sanic — through dedicated static parsers and framework-specific prompt templates. A rule-based parsing layer extracts per-endpoint context without invoking any language model. A Generation Agent then produces structured parameter documentation, which a Validation Agent independently verifies through up to three revision rounds; endpoints that fail verification are flagged for human review rather than passed forward silently. A Consistency Agent subsequently identifies cross-endpoint inconsistencies across the complete document set. A Test Generation Agent further produces test intents and pytest skeletons for each confirmed endpoint. Evaluation across all seven frameworks demonstrates robust detection and extraction performance, and analysis of validation false positives reveals four distinct failure categories with targeted remediation strategies identified for future refinement.

@inproceedings{zhao2026framework,
  author = {Zhao, Peng and Blake, John and Pyshkin, E.},
  title = {Framework-Adaptive Agentic Pipelines for API Knowledge Extraction and Test Generation},
  year = {2026},
  booktitle = {IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology}
}

Zhao, P., Blake, J., & Pyshkin, E. (2026). Framework-Adaptive Agentic Pipelines for API Knowledge Extraction and Test Generation. In IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology.

Authorship analysis is a challenging computational and linguistic task, which harnesses linguistic evidence to profile, verify, or attribute authorship. In forensic contexts, this task is complicated by limited and non-representative data, adversarial writing conditions (e.g. stylistic obfuscation), cross-genre comparison, and the requirements imposed by legal frameworks such as the Daubert criteria. A three-tier taxonomy of approaches is introduced, comprising expert-driven interpretive approaches, analytical similarity-based approaches, and predictive model-based approaches. Within this taxonomy, nine core methods are identified, ranging from expert linguistic reasoning and rule-based analysis to statistical, stylometric, machine-learning, deep-learning, LLM-based, and multi-agent pipeline approaches. The framework is sufficiently flexible to accommodate emerging analytical techniques. The paper concludes by arguing for an eclectic, evidence-aware approach to authorship analysis that prioritizes transparency and contextual validity.

@inproceedings{blake2026authorship,
  author = {Blake, John},
  title = {Authorship Analysis in the Age of AI: From Expert Reasoning to Multi-Agent Pipelines},
  year = {2026},
  booktitle = {Proceedings of the 14th International Conference on Information and Education Technology}
}

Blake, J. (2026). Authorship Analysis in the Age of AI: From Expert Reasoning to Multi-Agent Pipelines. In Proceedings of the 14th International Conference on Information and Education Technology.

The increasing volume of digital linguistic evidence and the expansion of virtual communicative spaces demand forensic linguistic tools that are both methodologically rigorous and accessible to a wider range of users, including legal practitioners. This paper introduces a bespoke, web-based authorship analysis tool designed to identify and visualize key textual patterns across questioned and known datasets. Operating through an intuitive graphical user interface, the tool offers an accessible alternative to command-line methods, expanding the reach of computational forensic linguistics to non-technical users. The tool integrates two core functionalities: (1) automated identification and comparison of shared n-grams, particularly bigrams and trigrams, within and between datasets, and (2) Key Word in Context (KWIC) exploration to support the interpretation of overlapping or distinctive lexical patterns. By combining these capabilities, the system enables both confirmatory and exploratory analysis of linguistic evidence, supporting investigations where authorship is contested or where stylistic consistency must be assessed. It has applications across the three domains of forensic linguistics: language as evidence, interaction in legal settings, and language of the law. In addition to its methodological contributions, the paper addresses key challenges in forensic semiotics: subjectivity, reproducibility, and transparency. It shows how computational approaches can mitigate the "subjectivity effect" by offering replicable, data-driven analyses of linguistic behaviour. Courtroom admissibility is also supported by producing clear, step-by-step analytical records and exportable logs that document each analytic operation. Our contribution aligns with the aims of computational forensic linguistics to enhance the interpretive rigour and evidentiary validity of linguistic analyses.

@article{blake2026bridging,
  author = {Blake, John and Kredens, Krzysztof},
  title = {Bridging Accessibility and Rigour: A Web App for Authorship Analysis Incorporating KWIC Exploration and Shared N-gram Profiling},
  year = {2026},
  journal = {International Journal of Semiotics and Law}
}

Blake, J., & Kredens, K. (2026). Bridging Accessibility and Rigour: A Web App for Authorship Analysis Incorporating KWIC Exploration and Shared N-gram Profiling. International Journal of Semiotics and Law.

This paper reports on a Design-Based Research (DBR) study investigating how human–AI interactions can be shaped to approximate the ways human assessors administer dynamic language assessments of pragmatic competence. While conversational AI is increasingly integrated into education, most applications remain text-based and overlook the pedagogical challenges of spoken interaction, particularly in pragmatics. Our project addresses this gap through the iterative design and evaluation of a computerised dynamic language assessment system focused on the speech act of requesting. Across six prototype cycles, users interacted with an AI interlocutor in spoken dialogues while an automated tutor agent monitored interactions for perceived instances of pragmatic inappropriateness and delivered graduated feedback. Analysis of iterative testing revealed distinct patterns in the types of issues encountered: surface-level problems in the graphical user interface (e.g., audio handling, text display, visuals) were relatively easy to resolve, whereas dialogue management, particularly phase disambiguation and parsing, proved more persistent and difficult to automate. These findings suggest that while technical refinements can steadily improve the usability of AI-mediated systems, replicating the subtle interactional and mediation strategies of human interlocutors remains a central challenge. By documenting these refinements, this study demonstrates how DBR can expose the boundary between tractable software improvements, prompt engineering fixes and deeper interactional complexities, providing practical insights for the design of AI-mediated spoken language learning environments.

@incollection{nicholas2026a,
  author = {Nicholas, A. and Blake, John and Mozgovoy, M.},
  title = {A Design-based Research Approach to Developing a Computerised Dynamic Assessment of Oral Pragmatic Competence: Solvable and Persistent Challenges},
  year = {2026},
  publisher = {Springer}
}

Nicholas, A., Blake, J., & Mozgovoy, M. (2026). A Design-based Research Approach to Developing a Computerised Dynamic Assessment of Oral Pragmatic Competence: Solvable and Persistent Challenges. In . Springer.

This chapter examines the challenges and opportunities presented by generative artificial intelligence (AI) in language education, focusing on its implications for policy development. Drawing on case studies of English language learners in Japan, the discussion highlights how generative AI tools can enhance learning by providing instant feedback, fostering critical engagement, and aiding technical communication. However, the misuse of AI to produce polished texts with minimal effort raises ethical concerns about academic integrity, fairness, and technological dependency. Three policy approaches are examined: banning generative AI, allowing its use, and actively encouraging its integration into educational practices. The chapter concludes that embracing generative AI in education, with appropriate guidance and training, prepares students to navigate AI-integrated environments effectively and ethically, aligning with the broader goal of equipping learners for a future shaped by technological advancements.

@inproceedings{blake2025policies,
  author = {Blake, John},
  title = {Policies for Generative AI in Language Education: Challenges and Choices},
  year = {2025},
  booktitle = {Proceedings of HKAECT 2025},
  publisher = {Springer}
}

Blake, J. (2025). Policies for Generative AI in Language Education: Challenges and Choices. In Proceedings of HKAECT 2025. Springer.

This study presents a multi-objective optimization framework integrating genetic algorithms with deep learning for spacecraft project management, addressing critical challenges in schedule prediction and cost forecasting. The methodology employs binary tournament selection with Pareto dominance ranking, simulated binary crossover (p_c = 0.9, n_c = 20), and CNN-LSTM hybrid architecture for temporal dependency modeling. Comparative analysis across six prediction methods demonstrates superior performance: RMSE of 34.7 days, MAPE of 8.3%, and R² of 0.847, achieving 79.3% accuracy within ±30-day windows and 92.6% within ±60-day windows. The framework attains 94.7% accuracy for baseline expenditure prediction and 73.4% accuracy for unplanned cost growth forecasting, substantially outperforming traditional parametric approaches (25–40% accuracy). These results validate the framework's capability to support data-driven resource allocation, risk-informed budget reserve planning, and proactive stakeholder communication in complex aerospace development programs, enabling more resilient project execution strategies. The framework demonstrates 73.4% accuracy in cost growth prediction compared to traditional 25–40% accuracy, enabling evidence-based decision support for billion-dollar aerospace initiatives.

@incollection{sungheetha2026enhanced,
  author = {Sungheetha, A. and Blake, John and Sharma, R. R. and Yogarayan, S. and Kannan, S.},
  title = {Enhanced AI-Driven Project Management Framework for Complex Space Exploration Missions: A Case Study Analysis of the James Webb Space Telescope},
  year = {2026},
  booktitle = {Proceedings of International Conference on Artificial Intelligence and Networks (ICAIN)},
  pages = {386--395},
  publisher = {Springer Nature Switzerland},
  doi = {10.1007/978-3-032-25617-1_28}
}

Sungheetha, A., Blake, J., Sharma, R., Yogarayan, S., & Kannan, S. (2026). Enhanced AI-Driven Project Management Framework for Complex Space Exploration Missions: A Case Study Analysis of the James Webb Space Telescope. In Proceedings of International Conference on Artificial Intelligence and Networks (ICAIN) (pp. 386-395). Springer Nature Switzerland. https://doi.org/10.1007/978-3-032-25617-1_28

This paper presents an innovative AI-enabled edge computing framework that integrates healthcare monitoring and energy management in smart cities through adaptive binning techniques. The proposed system combines distributed IoT sensors, blockchain-based secure data transmission, and neuromorphic computing to create a scalable infrastructure for urban health monitoring and energy optimization. Our framework addresses critical challenges in existing systems, including data privacy, energy efficiency, and real-time processing capabilities. The SMILE (Secure Middleware for Intelligent Life Enhancement) middleware serves as the core orchestration layer, managing distributed sensor networks while maintaining data security through federated Byzantine fault tolerance mechanisms. Compared to baseline cloud-centric and edge-only architectures, the implementation shows significant improvements in processing efficiency (47% faster than traditional cloud systems), reduction in energy consumption (38% compared to standard edge deployments) and diagnostic accuracy (93.5% versus 85% baseline accuracy). Experimental validation in 14 international deployment sites shows the system's adaptability to diverse urban environments with statistical significance (p<0.001). The framework's integration of adaptive histogram-based stream processing with custom neural networks enables effective management of distributed sensor networks while maintaining data security and system reliability.

@incollection{sungheetha2026bwidth,
  author = {Sungheetha, A. and Sharma, R. R. and Blake, John and Mahapatra, S. and Jeba Singh, O. and Dhawan, A.},
  title = {B_width Adaptive Binning Edge Computing Framework with AI for Smart City Healthcare Monitoring and Energy Management},
  year = {2026},
  booktitle = {Computer Vision and Robotics},
  pages = {43--57},
  publisher = {Springer Nature Switzerland},
  doi = {10.1007/978-3-032-14038-8_4}
}

Sungheetha, A., Sharma, R., Blake, J., Mahapatra, S., Jeba Singh, O., & Dhawan, A. (2026). B_width Adaptive Binning Edge Computing Framework with AI for Smart City Healthcare Monitoring and Energy Management. In Computer Vision and Robotics (pp. 43–57). Springer Nature Switzerland. https://doi.org/10.1007/978-3-032-14038-8_4

This paper presents a novel energy-efficient framework integrating Gallium Nitride (GaN) hardware accelerators with real-time stream processing for sustainable smart city IoT applications. The proposed system combines high-speed modulation characteristics of scaled GaN laser diodes operating at 2.4 GHz with reconfigurable Multiple-In Multiple-Out (MIMO) antenna arrays to enable efficient processing of intensive data streams from urban IoT sensors. The hybrid architecture leverages both edge and cloud computing paradigms, achieving statistically significant improvements of 47.7% in energy efficiency (95% CI: 44.2–51.3%, p<0.001) and 68.0% latency reduction (95% CI: 65.1–70.9%, p<0.001) compared to traditional approaches. The system incorporates resonant-cavity light-emitting diode technology for high-bandwidth data transmission and employs machine learning-based adaptive stream processing algorithms optimized for urban infrastructure monitoring. Experimental validation across 14 international deployments in Singapore, Barcelona, Toronto, and Dubai demonstrates consistent performance improvements while maintaining 99.8% system reliability and processing throughput of 8.7 Gbps.

@incollection{sungheetha2026energy,
  author = {Sungheetha, A. and Sharma, R. R. and Blake, John and Mahapatra, S. and Abeysinghe, N. and Parashar, K.},
  title = {Energy-Efficient GaN-Accelerated Stream Processing Framework for Smart City IoT Applications},
  year = {2026},
  booktitle = {Computer Vision and Robotics},
  pages = {381--394},
  publisher = {Springer Nature Switzerland},
  doi = {10.1007/978-3-032-14038-8_30}
}

Sungheetha, A., Sharma, R., Blake, J., Mahapatra, S., Abeysinghe, N., & Parashar, K. (2026). Energy-Efficient GaN-Accelerated Stream Processing Framework for Smart City IoT Applications. In Computer Vision and Robotics (pp. 381–394). Springer Nature Switzerland. https://doi.org/10.1007/978-3-032-14038-8_30

This paper introduces a dual-mode n-gram similarity detection tool specifically designed for corpus-based forensic authorship analysis. Intra-corpus mode is used to verify consistency within a dataset while inter-corpus mode is for comparison to a questioned dataset. Preliminary accuracy evaluation of shared n-gram detection is perfect at 100%.

@inproceedings{blake2026dual-mode,
  author = {Blake, John and Tamura, K. and Kredens, K.},
  title = {Dual-mode N-gram Similarity Detection for Forensic Authorship Analysis},
  year = {2026},
  booktitle = {Proceedings for 39th Pacific Asia Conference on Language, Information and Computation (PACLIC 39)}
}

Blake, J., Tamura, K., & Kredens, K. (2026). Dual-mode N-gram Similarity Detection for Forensic Authorship Analysis. In Proceedings for 39th Pacific Asia Conference on Language, Information and Computation (PACLIC 39).

Passive voice constructions vary in how explicitly they represent the agent, or doer of the action, ranging from clauses with fully stated agents to instances where the agent is omitted or difficult to infer. This paper introduces a multi-agentic system designed to automatically categorize English passive voice instances according to a four-level mystification index. The index ranges from Level 1, where the agent is explicitly stated, to Level 4, where the agent is maximally mystified, i.e., omitted and unrecoverable to casual readers without specialized knowledge. The system is implemented using LangChain and LangGraph, integrating PassivePy with multiple specialized agents dedicated to subtasks such as agent detection, inference, verification, and classification. Evaluation was conducted using manually annotated newspaper editorials. Results show that the system performs at expert-level accuracy when agents are explicit or guessable with certainty (Levels 1 and 2), while performance drops sharply in ambiguous or unknown cases (Levels 3 and 4). These findings demonstrate both the feasibility of automatic mystification analysis and the potential for future improvements in handling highly ambiguous contexts.

@inproceedings{blake2026multi-agentic,
  author = {Blake, John and Lingle, W. and Nguyen, D.T. and Pyshkin, E.},
  title = {Multi-agentic Automated Classification of Passive Voice Constructions by Mystification Level},
  year = {2026},
  booktitle = {Proceedings of the 20th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP 2025)},
  doi = {10.1109/iSAI-NLP66160.2025.11320469}
}

Blake, J., Lingle, W., Nguyen, D., & Pyshkin, E. (2026). Multi-agentic Automated Classification of Passive Voice Constructions by Mystification Level. In Proceedings of the 20th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP 2025). https://doi.org/10.1109/iSAI-NLP66160.2025.11320469

This paper presents the design and construction of WikiFirst, a corpus for investigating the impact of content variation on authorship similarity under a fixed genre. Prior work has investigated individual authorial style and impact of genre. However, the role of content has remained underexplored due to the lack of suitable data. We address this gap by constructing a Wikipedia-based corpus consisting exclusively of first revisions authored by non-anonymous editors, thereby ensuring high authorship certainty while maintaining a stable encyclopaedic genre.

@inproceedings{nguyen2026wikifirst,
  author = {Nguyen, D.T. and Sat, C.G. and Blake, John and Pyshkin, E.},
  title = {WikiFirst: A Genre-Fixed, Content-controlled Corpus for Evaluating Content Effects in Authorship Analysis},
  year = {2026},
  booktitle = {Proceedings of 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature co-located at the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2026), (pp},
  pages = {323--327}
}

Nguyen, D., Sat, C., Blake, J., & Pyshkin, E. (2026). WikiFirst: A Genre-Fixed, Content-controlled Corpus for Evaluating Content Effects in Authorship Analysis. In Proceedings of 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature co-located at the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2026), (pp (pp. 323--327).

Automated writing evaluation can be effective in providing support for L2 English learners. However, little research to date has investigated its use in the teaching of pragmatics in relation to L2 email writing, grounded in a sociocultural perspective on learning. We employ a quasi-experimental approach, investigating the effectiveness of a computerised dynamic assessment programme (C-DA) of L2 email writing, focusing on pragmatic development. The C-DA employs a developmentally sensitive approach, providing automated, immediate mediation to learners. The C-DA was administered twice – with a two-week delay between administrations – to a single group of 17 Japanese English L2 learner participants at a Japanese university; participants were 19–22 years of age with intermediate L2 proficiency levels. Text, identified pragmatic failure and mediation data were elicited from both administrations. Analysis of pragmatic failure frequency and explicitness of the mediation necessary for successful resolution of the identified pragmatic failure shows both frequency and explicitness decreasing not only within a round of administration, but also between rounds. Evidence of learner development was found across all types of pragmatic failure, including the requesting head act, email openings and closings. The study provides evidence to support a sociocultural approach to assessment and learning with regards to the pragmatics aspect of L2 email writing, in which mediation is sensitive to individual learners’ developmental needs. Further, findings support the use of a computerised approach to DA focusing on pragmatic competence, allowing for wider access to DA methodology among large learner group contexts.

@article{nicholas2026evaluating,
  author = {Nicholas, A. and Blake, John and Perkins, J. and Mozgovoy, M.},
  title = {Evaluating the effectiveness of a computerised dynamic assessment of L2 English email requests},
  year = {2026},
  journal = {Computer Assisted Language Learning},
  volume = {39},
  number = {1-2},
  pages = {303--335},
  doi = {10.1080/09588221.2024.2374775}
}

Nicholas, A., Blake, J., Perkins, J., & Mozgovoy, M. (2026). Evaluating the effectiveness of a computerised dynamic assessment of L2 English email requests. Computer Assisted Language Learning, 39(1-2), 303–335. https://doi.org/10.1080/09588221.2024.2374775

This study investigates the use of a pragmatics-focused computerized dynamic assessment (C-DA) of request-based L2 English email writing among Japanese university learners of English. The C-DA administers four email tasks to learners, automatically identifies perceived instances of pragmatic inappropriateness in texts and provides feedback, based on learner corpus perception data. The study compares the C-DA’s effectiveness in promoting learning among three participant groups: a graduated feedback group received feedback based on the concept of the zone of proximal development (ZPD); an explicit-only group received explicit feedback, and a control group did not receive feedback. The C-DA was administered twice, with a two-week delay between administrations. Both treatment groups showed evidence of development to a greater extent than the control both within a session and between sessions in terms of openings, closings and modification strategies. Comparing treatment groups, the graduated group responded more to feedback within a session for openings and closings, but not for modification strategies. Between sessions, there was no difference between treatment groups; however, across the entirety of the study, the graduated feedback group responded significantly more to feedback. Findings provide support for computerized approaches to L2 email writing feedback, and for approaches sensitive to a learner’s ZPD.

@article{nicholas2026impact,
  author = {Nicholas, A. and Blake, John and Perkins, J. and Mozgovoy, M.},
  title = {Impact of graduated versus explicit-only feedback in a computerized dynamic assessment of Japanese learners' L2 email writing},
  year = {2026},
  journal = {Applied Pragmatics},
  doi = {10.1075/ap.23018.nic}
}

Nicholas, A., Blake, J., Perkins, J., & Mozgovoy, M. (2026). Impact of graduated versus explicit-only feedback in a computerized dynamic assessment of Japanese learners' L2 email writing. Applied Pragmatics. https://doi.org/10.1075/ap.23018.nic

This paper presents an innovative approach combining triboelectric nanogenerators (TENG) with artificial intelligence for sustainable environmental monitoring. The proposed Adaptive Neural-TENG Integration System (ANTIS) addresses the challenges of power stability and efficiency in environmental sensing applications. By incorporating stream processing analytics through the LARA framework, our system achieves real-time data processing while optimizing energy harvesting efficiency. The methodology integrates neuromorphic computing principles with TENG-based power generation, achieving a 47% improvement in energy harvesting efficiency compared to conventional methods. Experimental results across 14 countries demonstrate the system's adaptability to various environmental conditions, with an average response time of 3.2ms and 92% accuracy in environmental parameter detection. This research contributes to the development of self-powered, intelligent environmental monitoring systems with potential applications in smart cities and precision agriculture.

@incollection{sungheetha2026ai-driven,
  author = {Sungheetha, A. and Blake, John and Sharma, R. R. and Mahapatra, S. and Jeba Singh, O.},
  title = {AI-Driven Sustainable Energy Harvesting System with Triboelectric Nanogenerators for Smart Environmental Monitoring},
  year = {2026},
  booktitle = {Proceedings of Fifth International Conference on Computing and Communication Networks},
  pages = {431--441},
  publisher = {Springer Nature Switzerland},
  doi = {10.1007/978-3-032-18910-3_39}
}

Sungheetha, A., Blake, J., Sharma, R., Mahapatra, S., & Jeba Singh, O. (2026). AI-Driven Sustainable Energy Harvesting System with Triboelectric Nanogenerators for Smart Environmental Monitoring. In Proceedings of Fifth International Conference on Computing and Communication Networks (pp. 431–441). Springer Nature Switzerland. https://doi.org/10.1007/978-3-032-18910-3_39

The creation of high-quality multiple-choice questions (MCQs) for language assessment is a labour-intensive task, often requiring careful balancing of linguistic appropriacy, proficiency level, topic coverage, and distractor plausibility. We present a modular, multi-agentic system built using LangChain to generate appropriate MCQs. Each agent in the system is responsible for a distinct task in the question generation pipeline. These tasks range from topic selection and question formation to answer validation, distractor generation, and coverage checks. The system supports flexible substitution of Large Language Models (LLMs), allowing comparative benchmarking across tasks in terms of generation accuracy and latency. Human expert assessment of item quality confirmed that the best-performing configurations yielded scores exceeding 95% in grammatical correctness with satisfactory speed. Our results demonstrate that multi-agent LLM-based architectures can effectively automate complex educational content creation workflows while offering transparency, modularity, and fine-grained controllability. The proposed system offers a reusable design pattern for intelligent educational content generation in broader domains.

@inproceedings{zhao2026a,
  author = {Zhao, P. and Blake, John and Pyshkin, E.},
  title = {A Modular Multi-Agentic Architecture for Automating Multiple-Choice Question Generation in Language Assessment},
  year = {2026},
  booktitle = {Proceedings of 7th International Conference on AI in Computational Linguistics, Procedia Computer Science, Elsevier},
  doi = {10.1016/j.procs.2026.01.070}
}

Zhao, P., Blake, J., & Pyshkin, E. (2026). A Modular Multi-Agentic Architecture for Automating Multiple-Choice Question Generation in Language Assessment. In Proceedings of 7th International Conference on AI in Computational Linguistics, Procedia Computer Science, Elsevier. https://doi.org/10.1016/j.procs.2026.01.070

Here we report on the development of the first Computerized Dynamic Assessment (C-DA) platform for pragmatic failure in request emails written by Japanese learners of English. Dynamic language assessments are usually dyadic interactions between the tutor and the learner. In our online C-DA, we harness natural language processing algorithms to detect specific instances of pragmatic failure in learner email texts. On matching, graduated feedback in the form of increasingly more explicit hints is displayed sequentially until either learners have appropriately revised the text or the allocated number of attempts is reached. The C-DA incorporates researcher- and learner-facing interfaces, automatically generates progress reports for learners, and tracks all activities for research purposes.

@incollection{blake2025computerized,
  author = {Blake, John and Mozgovoy, M. and Nicholas, A.},
  title = {Computerized Dynamic Assessment for pragmatic competence in second language learners' English email requests},
  year = {2025},
  booktitle = {Methodologies and Intelligent Systems for Technology Enhanced Learning Workshops -- 14th International Conference},
  pages = {17--28},
  publisher = {Springer},
  doi = {10.1007/978-3-031-85561-0_2}
}

Blake, J., Mozgovoy, M., & Nicholas, A. (2025). Computerized Dynamic Assessment for pragmatic competence in second language learners' English email requests. In Methodologies and Intelligent Systems for Technology Enhanced Learning Workshops -- 14th International Conference (pp. 17–28). Springer. https://doi.org/10.1007/978-3-031-85561-0_2

This paper presents a novel algorithm that leverages cutting-edge machine-learning techniques to accurately and efficiently detect AI-generated texts. Rapid advancements in natural language processing models have led to the generation of text closely resembling human language, making it increasingly difficult to differentiate between human and AI-generated content. However, misuse of such texts presents a serious and imminent threat to the quality of academic publishing. This underscores the urgent need for robust detection mechanisms to ensure information quality, maintain trust, and preserve the integrity of research publications. Our proposed model outperformed existing algorithms for accuracy with less computational complexity. The proposed model is a feature-based hybrid deep learning network that leverages part-of-speech tagging and integrates Bidirectional Long Short-Term Memory (Bi-LSTM) networks with Attention modules. The initial module extracts local contextual features using convolutional layers, followed by Bi-LSTM layers that capture long-term dependencies from past and future sequences. An attention mechanism highlights critical sequence components, enhancing the model’s focus on relevant data. The outputs from the attention and initial modules are concatenated through a residual connection, ensuring comprehensive feature representation. This combination is then fed into dense layers for final classification, effectively balancing feature richness and computational efficiency. The proposed model was evaluated on two benchmark datasets, achieving 85.00% and 88.00% accuracy, respectively.

@article{blake2025detection,
  author = {Blake, John and Miah, A.S.M. and Kredens, K. and Shin, J.},
  title = {Detection of AI-generated texts: A Bi-LSTM and attention-based approach},
  year = {2025},
  journal = {IEEE Access},
  volume = {13},
  pages = {71563--71576},
  doi = {10.1109/ACCESS.2025.3562750}
}

Blake, J., Miah, A., Kredens, K., & Shin, J. (2025). Detection of AI-generated texts: A Bi-LSTM and attention-based approach. IEEE Access, 13, 71563-71576. https://doi.org/10.1109/ACCESS.2025.3562750

This chapter investigates the interplay between ethical considerations and artificial intelligence (AI) in content production and interpretation by transcultural audiences, focusing on integrity, inclusivity, and impact. It argues for the enhancement of critical and digital literacy to assess the authenticity of AI-mediated narratives, the need for AI to support rather than replace human judgment in avoiding misinformation, and the development of human-centric AI systems that respect cultural subtleties and foster equitable representation. Through ethical frameworks, such as consequentialism, deontological ethics, virtue ethics, and the ethics of care, I advocate for AI that promotes truthfulness, mitigates biases, and respects diverse identities. Transparency and critical literacy are paramount in empowering audiences to demand diverse media narratives and the responsibility for ensuring AI-generated content does not perpetuate stereotypes is placed on both the users and creators of AI. This chapter calls for ethical AI deployment that aligns with human values and enhances global cultural discourse, showing the significance of ethical foresight and humanistic considerations in transcultural communications.

@incollection{blake2025ethics,
  author = {Blake, John},
  title = {The Ethics of AI in media: Crafting integrity, inclusivity, and impact},
  year = {2025},
  booktitle = {Transcultural Media Narratives: Cross-cultural Communication Insights},
  editor = {Camilo, E. and Bouziane, K.},
  pages = {229--254},
  publisher = {Labcom Publications}
}

Blake, J. (2025). The Ethics of AI in media: Crafting integrity, inclusivity, and impact. In E. Camilo & K. Bouziane (Eds.), Transcultural Media Narratives: Cross-cultural Communication Insights (pp. 229-254). Labcom Publications. https://labcom.ubi.pt/transcultural-media-narratives-cross-cultural-communication-insights/

This paper explores the transformative impact of LLMs on education and proposes an innovative solution: harnessing bimodal input and output as a means to boost, not bypass, the learning process. This proposed approach emphasizes the critical roles of synthesis and analysis within learning tasks. By structuring assignments in a manner that requires students to synthesize information from different sources to create suitable prompts for LLMs, the true potential of learning is reignited. Furthermore, students need to analyze the output of the LLM to create the required mode and format. This process necessitates a higher level of cognitive engagement, fostering critical thinking, creativity, and active learning. By interweaving textual and non-textual elements, the bimodal approach ensures that students are not merely recipients of information but active constructors of knowledge. By embracing the bimodal approach, the potential hindrance of LLMs is transformed into a powerful tool enriching and amplifying the learning process.

@incollection{blake2025learning,
  author = {Blake, John},
  title = {Learning in the age of LLMs: Boosting not bypassing the learning process},
  year = {2025},
  booktitle = {Transcending Boundaries in the Digital Age, Educational Communications and Technology Yearbook},
  editor = {S.K.K. Ng et al.},
  publisher = {Springer},
  doi = {10.1007/978-981-96-2921-3_9}
}

Blake, J. (2025). Learning in the age of LLMs: Boosting not bypassing the learning process. In S.K.K. Ng et al. (Ed.), Transcending Boundaries in the Digital Age, Educational Communications and Technology Yearbook. Springer. https://doi.org/10.1007/978-981-96-2921-3_9

This paper introduces the Feature Visualizer, an open-access AI-powered tool designed to raise genre awareness among novice academic writers through inductive learning, a process that includes approaches such as discovery learning. The tool houses an annotated corpus of scientific research articles written by computer science majors and allows learners to explore authentic texts using on-demand visualizations and multimodal explanations. By engaging with the corpus, learners identify recurring language patterns and rhetorical structures at macro, meso, and micro levels, facilitating the bottom-up discovery of genre conventions. A longitudinal study with Japanese undergraduate computer science majors showed that the tool enhanced learners’ awareness of academic writing conventions and genre features. Focus group interviews further confirmed the usability and pedagogical value of the Feature Visualizer. We conclude by discussing practical applications for genre-based writing instruction informed by inductive learning principles.

@article{blake2025raising,
  author = {Blake, John and Mozgovoy, M.},
  title = {Raising genre awareness though visualizing language features},
  year = {2025},
  journal = {Applied Corpus Linguistics},
  volume = {5},
  number = {3},
  pages = {100162},
  doi = {10.1016/j.acorp.2025.100162}
}

Blake, J., & Mozgovoy, M. (2025). Raising genre awareness though visualizing language features. Applied Corpus Linguistics, 5(3), 100162. https://doi.org/10.1016/j.acorp.2025.100162

Time series descriptions often accompany graphs to help readers focus on the key trends. Major English language proficiency tests, such as IELTS and TOEIC, incorporate such descriptions into their written examinations. Trend descriptions are, therefore, a high-stakes genre for learners of English aiming to study at universities in Anglophone countries. To help learners become more familiar with the genre and to provide language practice at an appropriate level, we developed TrendScribe. This is the first interactive online tool that enables users to generate textual descriptions of single-line graphs from user-submitted time series data. Both rule-based and LLM-based systems are used to generate textual descriptions. Complex datasets are preprocessed using a smoothing algorithm. Users can view descriptions at their preferred proficiency level, with each level offering a corresponding increase in lexical and grammatical complexity.

@incollection{blake2025trendscribe,
  author = {Blake, John and Zhao, Peng and Pyshkin, Evgeny},
  title = {TrendScribe: Design and Development of a Pedagogic Trend Description Generator for Learners of English},
  year = {2025},
  booktitle = {Proceedings of the 17th International Conference on Multi-disciplinary Trends in Artificial Intelligent, Springer Lecture Notes in Artificial Intlligence},
  editor = {C. Sombattheera, Weng, P. and Pang, J.},
  pages = {89--101},
  publisher = {Springer},
  doi = {10.1007/978-981-96-0692-4_8}
}

Blake, J., Zhao, P., & Pyshkin, E. (2025). TrendScribe: Design and Development of a Pedagogic Trend Description Generator for Learners of English. In Weng C. Sombattheera & J. Pang (Eds.), Proceedings of the 17th International Conference on Multi-disciplinary Trends in Artificial Intelligent, Springer Lecture Notes in Artificial Intlligence (pp. 89-101). Springer. https://doi.org/10.1007/978-981-96-0692-4_8

This study investigates the potential for Large Language Models (LLMs) to scale-up Dynamic Assessment (DA). To facilitate such an investigation, we first developed DynaWrite—a modular, microservices-based grammatical tutoring application which supports multiple LLMs to generate dynamic feedback to learners of English. Initial testing of 21 LLMs, revealed GPT-4o and neural-chat to have the most potential to scale-up DA in the language learning classroom. Further testing of these two candidates found both models performed similarly in their ability to accurately identify grammatical errors in user sentences. However, GPT-4o consistently outperformed neural-chat in the quality of its DA by generating clear, consistent, and progressively explicit hints. Real-time responsiveness and system stability were also confirmed through detailed performance testing, with GPT-4o exhibiting sufficient speed and stability. This study shows that LLMs can be used to scale-up dynamic assessment and thus enable dynamic assessment to be delivered to larger groups than possible in traditional teacher-learner settings.

@article{jaganov2025large,
  author = {Jaganov, T. and Blake, John and Villegas, J. and Carr, N.},
  title = {Large Language Model-Driven Dynamic Assessment of Grammatical Accuracy in English Language Learner Writing},
  year = {2025},
  journal = {IEEE Access},
  volume = {13},
  pages = {151538--151550},
  doi = {10.1109/ACCESS.2025.3603191}
}

Jaganov, T., Blake, J., Villegas, J., & Carr, N. (2025). Large Language Model-Driven Dynamic Assessment of Grammatical Accuracy in English Language Learner Writing. IEEE Access, 13, 151538-151550. https://doi.org/10.1109/ACCESS.2025.3603191

We present VR Math Bridge, a virtual reality (VR)-based application designed to enhance calculus education by combining immersive virtual environments with artificial intelligence (AI)-driven teaching assistance. VR Math Bridge creates a virtual classroom where students interact with Khan Academy videos and a 3D AI assistant that provides real-time, personalized feedback to their questions. This system leverages a floating panel for chapter selection, a virtual blackboard for video playback, and Cognitive 3D for analyzing user engagement. To demonstrate the system’s capabilities, we developed a prototype on Quest 3, focusing on derivatives as the initial test topic. We conducted a preliminary subjective evaluation (n=2) of the prototype to collect early insights for future user study evaluation.

@inproceedings{lai2025vr,
  author = {Lai, H.S. and Nassani, A. and Blake, John and Villegas, J.},
  title = {VR Math Bridge: Bridging Interactivity in Online Education with AI and VR},
  year = {2025},
  booktitle = {Proceedings of the IEEE Gaming, Entertainment, and Media Conference (IEEE GEM 2025)},
  publisher = {IEEE},
  doi = {10.1109/GEM66882.2025.11155841}
}

Lai, H., Nassani, A., Blake, J., & Villegas, J. (2025). VR Math Bridge: Bridging Interactivity in Online Education with AI and VR. In Proceedings of the IEEE Gaming, Entertainment, and Media Conference (IEEE GEM 2025). IEEE. https://doi.org/10.1109/GEM66882.2025.11155841

We introduce a novel approach to language learning leveraging digital humans as adaptive tutors within immersive XR environments. Our system’s novelty lies in the use of biosignals, specifically real-time heart rate data, collected from a Samsung Watch 7, to dynamically adapt the learning experience. The digital human tutor adjusts its behavior, feedback, and the difficulty of the learning content based on the learner’s inferred cognitive and emotional state. We present the fully developed system architecture, which integrates a customizable digital human powered by ConvAI, LLM, an XR environments, and a data streaming pipeline. While human participant testing is planned, preliminary insights from the system’s development demonstrate the technical feasibility of this approach. This research has the potential to significantly enhance language learning outcomes, engagement, and motivation by creating more personalized, and engaging learning experiences, paving the way for a new generation of adaptive educational technologies.

@inproceedings{nassani2025adaptive,
  author = {Nassani, A. and Blake, John and Villegas, J.},
  title = {Adaptive Learning Companions: Enhancing Education with Biosignal-Driven Digital Human},
  year = {2025},
  booktitle = {Proceedings of the Extended Abstracts of the Conference on Human Factors in Computing Systems, CHI 2025},
  doi = {10.1145/3706599.3719877}
}

Nassani, A., Blake, J., & Villegas, J. (2025). Adaptive Learning Companions: Enhancing Education with Biosignal-Driven Digital Human. In Proceedings of the Extended Abstracts of the Conference on Human Factors in Computing Systems, CHI 2025. https://doi.org/10.1145/3706599.3719877

In this paper, we provide a proof-of-concept for a computerized diagnostic language assessment (C-DLA) of spoken requesting among Japanese learners of English at a Japanese computer science university. The program focuses on the pragmatics aspect of spoken communication, in which the language choices we make are affected by socio-contextual factors such as relative social status and familiarity with the interlocutor. In so doing, the C-DLA aims to address a number of challenges. Requesting is an important, but challenging skill for many learners, and yet is also undertaught in the language classroom, due to time and resource constraints. Further, assessments typically evaluate the learner holistically, providing an overall score, without providing insight into specific aspects of the learner's performance. A C-DLA addresses these challenges by employing a three-stage process: i) assessment administration; ii) provision of immediate individualized feedback to the learner that promotes learning, and iii) further instruction provision, based on the assessment results. Computerization of the DLA widens access, allowing large numbers of learners to engage with the program simultaneously. Here, we provide a rationale for the C-DLA and an outline of the key challenges — namely, speech recognition of L2 English, identification of pragmatic inappropriateness in a learner's interactive speaking performance and automated feedback delivery. We further provide a proof-of-concept for the C-DLA, in which the program administers a number of interactive spoken requesting tasks to the learner, acts as an automated spoken dialogue interlocutor, and provides immediate, automated pragmatics-focused feedback when necessary.

@inproceedings{nicholas2025computerized,
  author = {Nicholas, A. and Mozgovoy, M. and Blake, John},
  title = {Computerized Diagnostic Language Assessment of Oral Requesting-in-interaction: Proof-of-concept},
  year = {2025},
  booktitle = {Proceedings of 13th International Conference on Information and Education Technology},
  publisher = {IEEE Xplore},
  doi = {10.1109/ICIET66371.2025.11046328}
}

Nicholas, A., Mozgovoy, M., & Blake, J. (2025). Computerized Diagnostic Language Assessment of Oral Requesting-in-interaction: Proof-of-concept. In Proceedings of 13th International Conference on Information and Education Technology. IEEE Xplore. https://doi.org/10.1109/ICIET66371.2025.11046328

Using the linguistic methods of metaphor, discourse, and comparative analysis, this study presents the problem of authentic translation of the composition titles from Tchaikovsky’s Children’s Album, Op. 39, for English editions or concert programs. We examine this problem from the perspective of the origins of this piano masterpiece and its subsequent transformations. Among many other factors, reordering of the compositions influenced the editorial decisions on selecting the proper equivalents for titles in English. Specifically, we explore how appropriate translations of the composition titles can help in preserving the important historical and cultural connotations and musical authenticity of the 24 piano pieces known as the Children’s Album, and therefore contribute to a better understanding of the whole original masterpiece, particularly in light of the significant reordering of the pieces in the first published edition compared to the original manuscript. By comparing the number of canonical known editions, we suggest a model designed to address the evident “lost in translation” issues in existing editions and resources.

@article{pyshkin2025lost,
  author = {Pyshkin, E. and Blake, John},
  title = {"Lost in Translation"? Challenges in Conveying the Original Titles of Tchaikovsky's Children's Album},
  year = {2025},
  journal = {Terra Linguistica},
  volume = {16},
  number = {1},
  pages = {99--111},
  doi = {10.18721/JHSS.16107}
}

Pyshkin, E., & Blake, J. (2025). "Lost in Translation"? Challenges in Conveying the Original Titles of Tchaikovsky's Children's Album. Terra Linguistica, 16(1), 99-111. https://doi.org/10.18721/JHSS.16107

This research contributes to the studies on the origins and transformations of Tchaikovsky's Children's Album, Op. 39 using the linguistic methods of discourse, metaphor, and comparative analysis to explore a number of connected questions and their impact on how the audiences and scholars perceive and understand the compositions. These methods are supported by the technology provided by computational linguistics, such as large language models along with music analysis algorithms based on signature pattern elicitation. This article examines how artificial intelligence technologies can shed light on the differing views on the Children's Album. The meanings and implications of the published reordering of the pieces are explored. The influence of Schumann's Album for the Young and the broader pedagogical and cultural significance of editorial transformations is investigated. Through this interdisciplinary approach, this study offers new insights into the compositional intent and interpretive possibilities of Tchaikovsky's work. The presented results of the musicology, literary, computational, and linguistic analyses complement the few scholarly studies aimed at unveiling the intriguing metaphors and connections of the Children's Album, which tend to remain in the shadows of his larger-scale piano and symphonic works.

@article{pyshkin2025restoring,
  author = {Pyshkin, E. and Blake, John},
  title = {Restoring Authenticity: Literary, Linguistic, and Computational Study of the Manuscripts of Tchaikovsky's Children's Album},
  year = {2025},
  journal = {Arts},
  volume = {14},
  doi = {10.3390/arts14030049}
}

Pyshkin, E., & Blake, J. (2025). Restoring Authenticity: Literary, Linguistic, and Computational Study of the Manuscripts of Tchaikovsky's Children's Album. Arts, 14. https://doi.org/10.3390/arts14030049

@inproceedings{pyshkin2025virtualization,
  author = {Pyshkin, E. and Sato, R. and Nassani, A. and Blake, John},
  title = {Virtualization for Kintsugi Art: Damaged Porcelain Figurine Recreation Supported by 3D Modeling Computer Technology},
  year = {2025},
  booktitle = {Proceedings of ARTeFACTo 2024: 4th International Conference on Digital Creation in Arts, Media and Technology}
}

Pyshkin, E., Sato, R., Nassani, A., & Blake, J. (2025). Virtualization for Kintsugi Art: Damaged Porcelain Figurine Recreation Supported by 3D Modeling Computer Technology. In Proceedings of ARTeFACTo 2024: 4th International Conference on Digital Creation in Arts, Media and Technology. https://books.usj.edu.mo/index.php/usj-acaedemicpress/catalog/book/27

This paper explores the extent to which stylistic features contribute to the task of authorship attribution in forensic contexts. Drawing on a filtered subset of the Enron email corpus, the study operationalizes stylistic indicators across four groups: lexical, syntactic, orthographic, and discoursal. Using R Programming Language for feature engineering and logistic regression modelling, we systematically assessed both the individual and interactive effects of these features on attribution accuracy. Results show that n-gram similarity consistently outperformed all other features, with the combined model of n-gram similarity and its interaction with other features achieving accuracy, precision and F1 scores of 91.6%, 93.3% and 91.7% respectively. The model was subsequently evaluated on a subset of the TEL corpus to assess its applicability in a forensic setting. The findings highlight the dominant role of lexical similarity and suggest that integrating interaction effects can yield further performance gains in forensic authorship analysis.

@inproceedings{sat2025modelling,
  author = {Sat, G.C. and Blake, John and Pyshkin, E.},
  title = {Modelling the Relative Contributions of Stylistic Features in Forensic Authorship Attribution},
  year = {2025},
  booktitle = {Proceedings for the Recent Advances in Natural Language Processing 2025 Conference}
}

Sat, G., Blake, J., & Pyshkin, E. (2025). Modelling the Relative Contributions of Stylistic Features in Forensic Authorship Attribution. In Proceedings for the Recent Advances in Natural Language Processing 2025 Conference. https://acl-bg.org/proceedings/2025/RANLP%202025/index.html

The emerging field of virtual reality (VR) therapies in diverse therapeutic settings is examined in this chapter's investigation. We provide the most recent literature highlighting an important developments and obstacles in VR therapy research. There are two innovative approaches introduced: a VR-based motor rehabilitation program for stroke patients and an adaptive VR experience rehabilitation scheme for concern disorders. The machine learning algorithms and highly developed haptic feedback are used in this method to improve the treatment results. The result of the proposed approach is compared with the conventional therapeutic approaches. Our proposed system shows a major improvement in both patient engagement and treatment efficiency. The proposed approaches leverage the immersive capabilities of the healthcare metaverse to deliver personalized VR-based motor rehabilitation for stroke patients and adaptive VR exposure therapy for anxiety disorders, utilizing machine learning algorithms and advanced haptic feedback to create a seamless, interactive therapeutic environment that significantly enhances patient engagement and treatment efficacy compared to conventional methods. Many more personalized and successful therapeutic interventions are made possible by the research, which contributes to the continuous development of VR treatments.

@inproceedings{sungheetha2025adaptive,
  author = {Sungheetha, A. and Sharma, R.R. and Blake, John and Sreeja, B.P.},
  title = {Adaptive virtual reality exposure therapy and motor rehabilitation from Hebbian learning rule in metaverse},
  year = {2025},
  booktitle = {In Healthcare Frontiers in the Metaverse: Innovations and Impacts, (pp. 227-243)},
  pages = {227--243},
  doi = {10.1016/B978-0-443-32998-2.00017-2}
}

Sungheetha, A., Sharma, R., Blake, J., & Sreeja, B. (2025). Adaptive virtual reality exposure therapy and motor rehabilitation from Hebbian learning rule in metaverse. In In Healthcare Frontiers in the Metaverse: Innovations and Impacts, (pp. 227-243) (pp. 227-243). https://doi.org/10.1016/B978-0-443-32998-2.00017-2

@inproceedings{sungheetha2025analysis,
  author = {Sungheetha, A. and Blake, John and Adere, K. and Shifaw, B.},
  title = {Analysis and identification of gout flares using machine learning},
  year = {2025},
  booktitle = {In Diagnosing Musculoskeletal Conditions using Artifical Intelligence and Machine Learning to Aid Interpretation of Clinical Imaging, (pp. 179-194)},
  pages = {179--194},
  doi = {10.1016/B978-0-443-32892-3.00010-5}
}

Sungheetha, A., Blake, J., Adere, K., & Shifaw, B. (2025). Analysis and identification of gout flares using machine learning. In In Diagnosing Musculoskeletal Conditions using Artifical Intelligence and Machine Learning to Aid Interpretation of Clinical Imaging, (pp. 179-194) (pp. 179-194). https://doi.org/10.1016/B978-0-443-32892-3.00010-5

@inproceedings{sungheetha2025smart,
  author = {Sungheetha, A. and Mahapatra, S. and Blake, John and Aroba, O.J. and Ghantasala, G.S.P.},
  title = {Smart Underwater Acoustic Monitoring with Knowledge Distillation and FOPT Feature Fusion for Optimization},
  year = {2025},
  booktitle = {Proceedings of the 2nd International Conference on New Frontiers in Communication, Automation, Management and Security},
  doi = {10.1109/ICCAMS65118.2025.11234166}
}

Sungheetha, A., Mahapatra, S., Blake, J., Aroba, O., & Ghantasala, G. (2025). Smart Underwater Acoustic Monitoring with Knowledge Distillation and FOPT Feature Fusion for Optimization. In Proceedings of the 2nd International Conference on New Frontiers in Communication, Automation, Management and Security. https://doi.org/10.1109/ICCAMS65118.2025.11234166

Teaching philosophy statements are often declarations of beliefs interspersed with descriptions and metaphors. The disjuncture between the stated philosophy and actual teaching has been raised by numerous academics. This case study addresses the neglected area of grounding teaching philosophies on actual teacher behaviour rather than on espoused beliefs. This study includes a replicable framework for teachers to create evidence-based teaching philosophy statements through a systematic investigation of their actual teaching practices. A retrospective think-aloud protocol was used to recount a lesson. Using a transcript of the recount, the teacher's actions were identified, extracted, and justified following pre-determined protocols. References to theoretical and empirical studies supporting or contradicting the justifications were checked in the research literature. To counteract potential self-bias, colleagues' views on the reasons selected were surveyed. The discrepancy between the teacher's justification of actions and the peers' perspectives revealed hitherto hidden idiosyncrasies and underlying values.

@article{blake2024aligning,
  author = {Blake, John},
  title = {Aligning teaching philosophy statements with practice: An evidence-based approach using retrospective think-aloud protocols},
  year = {2024},
  journal = {Education Sciences},
  volume = {14},
  number = {7},
  pages = {795},
  doi = {10.3390/educsci14070795}
}

Blake, J. (2024). Aligning teaching philosophy statements with practice: An evidence-based approach using retrospective think-aloud protocols. Education Sciences, 14(7), 795. https://doi.org/10.3390/educsci14070795

This paper discusses the challenges posed in creating a Computer-Assisted Pronunciation Training (CAPT) environment for multiple languages. By selecting one language from each of three different language families, we show that a single environment may be tailored to cater for different target languages. We detail the challenges faced during the development of a multimodal CAPT environment comprising a toolkit that manages mobile applications using speech signal processing, visualization, and estimation algorithms. Since the applied underlying mathematical and phonological models, as well as the feedback production algorithms, are based on sound signal processing and modeling rather than on particular languages, the system is language-agnostic and serves as an open toolkit for developing phrasal intonation training exercises for an open selection of languages. However, it was necessary to tailor the CAPT environment to the language-specific particularities in the multilingual setups, especially the additional requirements for adequate and consistent speech evaluation and feedback production. In our work, we describe our response to the challenges in visualizing and segmenting recorded pitch signals and modeling the language melody and rhythm necessary for such a multilingual adaptation, particularly for tonal syllable-timed and mora-timed languages.

@article{blake2024an,
  author = {Blake, John and Bogach, N. and Kusakari, A. and Lezhenin, I. and Khaustova, V. and Xuan, S.L. and Nguyen, V.N. and Pham, N.B. and Svechnikov, R. and Ostapchuk, A. and Efimov, D. and Pyshkin, E.},
  title = {An Open CAPT System for Prosody Practice: Practical Steps Towards Multilingual Setup},
  year = {2024},
  journal = {Languages},
  volume = {9},
  number = {1},
  pages = {27},
  doi = {10.3390/languages9010027}
}

Blake, J., Bogach, N., Kusakari, A., Lezhenin, I., Khaustova, V., Xuan, S., Nguyen, V., Pham, N., Svechnikov, R., Ostapchuk, A., Efimov, D., & Pyshkin, E. (2024). An Open CAPT System for Prosody Practice: Practical Steps Towards Multilingual Setup. Languages, 9(1), 27. https://doi.org/10.3390/languages9010027

Skin cancer poses a significant healthcare challenge, requiring precise and prompt diagnosis for effective treatment. While recent advances in deep learning have dramatically improved medical image analysis, including skin cancer classification, ensemble methods offer a pathway for further enhancing diagnostic accuracy. This study introduces a cutting-edge approach employing the Max Voting Ensemble Technique for robust skin cancer classification on ISIC 2018: Task 1-2 dataset. We incorporate a range of cutting-edge, pre-trained deep neural networks, including MobileNetV2, AlexNet, VGG16, ResNet50, DenseNet201, DenseNet121, InceptionV3, ResNet50V2, InceptionResNetV2, and Xception. These models have been extensively trained on skin cancer datasets, achieving individual accuracies ranging from 77.20% to 91.90%. Our method leverages the synergistic capabilities of these models by combining their complementary features to elevate classification performance further. In our approach, input images undergo preprocessing for model compatibility. The ensemble integrates the pre-trained models with their architectures and weights preserved. For each skin lesion image under examination, every model produces a prediction. These are subsequently aggregated using the max voting ensemble technique to yield the final classification, with the majority-voted class serving as the conclusive prediction. Through comprehensive testing on a diverse dataset, our ensemble outperformed individual models, attaining an accuracy of 93.18% and an AUC score of 0.9320, thus demonstrating superior diagnostic reliability and accuracy. We evaluated the effectiveness of our proposed method on the HAM10000 dataset to ensure its generalizability. Our ensemble method delivers a robust, reliable, and effective tool for the classification of skin cancer. By utilizing the power of advanced deep neural networks, we aim to assist healthcare professionals in achieving timely and accurate diagnoses, ultimately reducing mortality rates and enhancing patient outcomes.

@article{hossain2024combining,
  author = {Hossain, M.M. and Hossain, M.M. and Arefin, M.B. and Akhtar, F. and Blake, John},
  title = {Combining State-of-the-Art Pre-Trained Deep Learning Models: A Noble Approach for Skin Cancer Detection Using Max Voting Ensemble},
  year = {2024},
  journal = {Diagnostics},
  volume = {14},
  number = {1},
  doi = {10.3390/diagnostics14010089}
}

Hossain, M., Hossain, M., Arefin, M., Akhtar, F., & Blake, J. (2024). Combining State-of-the-Art Pre-Trained Deep Learning Models: A Noble Approach for Skin Cancer Detection Using Max Voting Ensemble. Diagnostics, 14(1). https://doi.org/10.3390/diagnostics14010089

This study evaluates a computerized dynamic assessment (C-DA) method's potential to build a detailed pragmatics-focused developmental profile of a Japanese L2 English learner's L2 email writing. L2 email writing studies typically separate learning and assessment, using holistic scales to evaluate the pragmatic elements of learner texts. C-DA, grounded in sociocultural theory, unifies learning and assessment, administering email tasks with varying social contexts and providing immediate mediation within the learner's zone of proximal development (ZPD). Further, a diagnostic capacity allows for identification of specific pragmatics-related infelicities. The C-DA employs a dual-layered framework: an identification layer uses a coding scheme to automatically identify specific instances of perceived pragmatic inappropriateness, while the mediation layer provides ZPD-sensitive mediation. By evaluating the frequency and explicitness of mediation engaged in, in combination with qualitative examination of elicited email texts, the C-DA enables insights into learner development within the ZPD. We focus on an individual learner's interaction with the C-DA, evaluating the program's effectiveness in enabling a detailed learner diagnostic and developmental profile.

@article{nicholas2024profiling,
  author = {Nicholas, A. and Blake, John},
  title = {Profiling learner development through the application of a computerized dynamic assessment methodology to a Japanese learner's L2 English email writing},
  year = {2024},
  journal = {Research Methods in Applied Linguistics},
  volume = {3},
  number = {3},
  doi = {10.1016/j.rmal.2024.100164}
}

Nicholas, A., & Blake, J. (2024). Profiling learner development through the application of a computerized dynamic assessment methodology to a Japanese learner's L2 English email writing. Research Methods in Applied Linguistics, 3(3). https://doi.org/10.1016/j.rmal.2024.100164

@incollection{pyshkin2024dispelling,
  author = {Pyshkin, E. and Blake, John},
  title = {Dispelling the seven myths of Tchaikovsky's Children's Album through computational and language modeling},
  year = {2024},
  editor = {E. Himonides, Johnson, C., Prior, H., and King, A.},
  pages = {29--31},
  doi = {10.17605/OSF.IO/WE2AV}
}

Pyshkin, E., & Blake, J. (2024). Dispelling the seven myths of Tchaikovsky's Children's Album through computational and language modeling. In Johnson E. Himonides & A. King (Eds.), (pp. 29-31). https://doi.org/10.17605/OSF.IO/WE2AV

This paper examines the plateau effect and the role of Computer-Assisted Pronunciation Training (CAPT) in enabling learners to move beyond the plateau. Specifically, the samples and empirical evidence for this study is provided by StudyIntonation, a top-down CAPT environment supporting visual display of phrasal intonation in the form of pitch graphs presented for both the model pitch of native speakers and attempts of learners. Utterances of model speakers are grouped by situational context, prosodic forms and mode of feedback. The system largely relies upon concepts of sociocultural theory, such as mediation through the zone of proximal development. With the help of an experimental group of high school students, we use mathematical models to pinpoint the Zone of Proximal Development (ZPD), allowing for delivery of tailored task classification based on syntax and discourse tags. Longitudinal pronunciation assessment supported by dynamic time warping and cross-recurrence quantification analysis is used to locate the ZPD, and provide personalized practice. Preliminary experiments for the current study demonstrate that this approach can help learners in overcoming the plateau effect experienced during the learning process. The reported new findings create further grounds for improving and targeting the CAPT system feedback to learners with respect to their individual achievements and differences in learning styles.

@article{pyshkin2024moving,
  author = {Pyshkin, E. and Blake, John and Bogach, N.},
  title = {Moving beyond the plateau with computer-assisted pronunciation mediation},
  year = {2024},
  journal = {International Journal of Information and Education Technology},
  volume = {14},
  number = {6},
  pages = {890--897},
  doi = {10.18178/ijiet.2024.14.6.2115}
}

Pyshkin, E., Blake, J., & Bogach, N. (2024). Moving beyond the plateau with computer-assisted pronunciation mediation. International Journal of Information and Education Technology, 14(6), 890-897. https://doi.org/10.18178/ijiet.2024.14.6.2115

@inproceedings{pyshkin2024multimodal,
  author = {Pyshkin, E. and Blake, John and Khaustova, V. and Khaustov, V. and Lezhenin, I. and Svechnikov, R. and Bogach, N.},
  title = {Multimodal contextualizing and targeting exercises in iCAPT system},
  year = {2024},
  booktitle = {Proceedings of INTED 2024, (pp},
  pages = {438--448},
  publisher = {IATED},
  doi = {10.21125/inted.2024.0164}
}

Pyshkin, E., Blake, J., Khaustova, V., Khaustov, V., Lezhenin, I., Svechnikov, R., & Bogach, N. (2024). Multimodal contextualizing and targeting exercises in iCAPT system. In Proceedings of INTED 2024, (pp (pp. 438-448). IATED. https://doi.org/10.21125/inted.2024.0164

@inproceedings{pyshkin2024transfigured,
  author = {Pyshkin, E. and Sato, R. and Nassani, A. and Blake, John},
  title = {"Transfigured Reminiscence": A Vintage Porcelain Figurine Reborn Through 3D Virtualization and Kintsugi Art},
  year = {2024},
  booktitle = {Proceedings of the 5th Kyoto Conference on Arts, Media and Culture, (pp},
  pages = {179--187},
  doi = {10.22492/issn.2436-0503.2024.17}
}

Pyshkin, E., Sato, R., Nassani, A., & Blake, J. (2024). "Transfigured Reminiscence": A Vintage Porcelain Figurine Reborn Through 3D Virtualization and Kintsugi Art. In Proceedings of the 5th Kyoto Conference on Arts, Media and Culture, (pp (pp. 179-187). https://doi.org/10.22492/issn.2436-0503.2024.17

@inproceedings{tamura2024finer-grained,
  author = {Tamura, K. and Blake, John},
  title = {Finer-grained part-of-speech classification of adjectives},
  year = {2024},
  booktitle = {Proceedings of The Japanese Society for Language Sciences 25th Annual International Conference (pp},
  pages = {182--183}
}

Tamura, K., & Blake, J. (2024). Finer-grained part-of-speech classification of adjectives. In Proceedings of The Japanese Society for Language Sciences 25th Annual International Conference (pp (pp. 182-183).

@inproceedings{blake2023automatic,
  author = {Blake, John and Pyshkin, E. and Pavlic, S.},
  title = {Automatic detection and visualization of information structure in English},
  year = {2023},
  booktitle = {Proceedings of the 6th International Conference on Natural Language Processing and Information Retrieval},
  pages = {200--204},
  publisher = {ACM},
  doi = {10.1145/3582768.3582784}
}

Blake, J., Pyshkin, E., & Pavlic, S. (2023). Automatic detection and visualization of information structure in English. In Proceedings of the 6th International Conference on Natural Language Processing and Information Retrieval (pp. 200-204). ACM. https://doi.org/10.1145/3582768.3582784

With the burgeoning growth of the metaverse and online virtual environments, new security challenges have been introduced that require careful exploration and mitigation. An increasing proportion of human interactions and transactions now take place in these digital spaces, making it essential to protect users and ensure the safety and integrity of virtual worlds. This chapter explores three dimensions of this issue. First, through a study of the types of crimes that occur in these environments, to gain a holistic under- standing of the cybercrime technoscape. Second, the authors use a two-pronged approach to increase the safety of the metaverse by targeting both potential perpetrators and victims. This is achievable by identifying indicators that may be used to detect potential perpetrators or victims. Thirdly and finally, strategies and techniques to make these online communities safer are suggested.

@incollection{blake2023blake,
  author = {Blake, John and In Elshenraki, H.},
  title = {Blake, J},
  year = {2023},
  editor = {the Metaverse: A Study on Classification, Prediction, and Mitigation Strategies. In Elshenraki, H.},
  pages = {66--77},
  publisher = {IGI Global},
  doi = {10.4018/979-8-3693-0220-0.ch004}
}

Blake, J., & In Elshenraki, H. (2023). Blake, J. In Prediction the Metaverse: A Study on Classification & H. Mitigation Strategies. In Elshenraki (Eds.), (pp. 66-77). IGI Global. https://doi.org/10.4018/979-8-3693-0220-0.ch004

@incollection{blake2023intelligent,
  author = {Blake, John},
  title = {Intelligent CALL: Individualizing learning using natural language generation},
  year = {2023},
  editor = {A.W.B. Tso, Ng, S.K.K., Law, L., and Bai, T.S.},
  pages = {3--18},
  publisher = {Springer},
  doi = {10.1007/978-981-19-9217-9_1}
}

Blake, J. (2023). Intelligent CALL: Individualizing learning using natural language generation. In Ng A.W.B. Tso & T.S. Bai (Eds.), (pp. 3-18). Springer. https://doi.org/10.1007/978-981-19-9217-9_1

@inproceedings{blake2023linguistic-first,
  author = {Blake, John and Tamura, K. and Pyshkin, E.},
  title = {Linguistic-first approach to learning Python for natural language generation: Problem breakdown to pseudocode},
  year = {2023},
  booktitle = {Conference Proceedings of the 5th International Conference on ICT Integration in Technical Education, 2909 (1), 020002},
  pages = {020002},
  doi = {10.1063/5.0183649}
}

Blake, J., Tamura, K., & Pyshkin, E. (2023). Linguistic-first approach to learning Python for natural language generation: Problem breakdown to pseudocode. In Conference Proceedings of the 5th International Conference on ICT Integration in Technical Education, 2909 (1), 020002 (pp. 020002). https://doi.org/10.1063/5.0183649

This article shows how a service quality model can be applied by language teachers to improve student satisfaction. Improvements in student satisfaction, however, do not necessary correlate with improvements in teaching ability. Exceeding the low expectations of students results in high degrees of satisfaction, but meeting the high expectations of students may not result in satisfaction. This article introduces the theoretical background, presents a model of service quality for language teaching, and shows how this model can be applied through three case studies. The article concludes with practical suggestions on how teachers of language can increase student satisfaction levels by meeting and exceeding the expectations of students.

@inproceedings{blake2023surprise,
  author = {Blake, John},
  title = {Surprise and delight: Application of a service quality model to language teaching},
  year = {2023},
  booktitle = {Proceedings (pp},
  pages = {5616--5623},
  doi = {10.21125/inted.2023.1467}
}

Blake, J. (2023). Surprise and delight: Application of a service quality model to language teaching. In Proceedings (pp (pp. 5616-5623). https://doi.org/10.21125/inted.2023.1467