IEEE Transactions on Learning Technologies最新文献

{"title":"Profiling Preschool Teachers' Readiness for AI-Enhanced Professional Development: A Diagnostic Framework Based on Digital Literacy","authors":"Huihua He;Tingjun You;Wenwei Luo;Ilene R. Berson;Michael J. Berson;Lei Zhou;Linzhu Fan;Xiongwei Xu","doi":"10.1109/TLT.2026.3675859","DOIUrl":"https://doi.org/10.1109/TLT.2026.3675859","url":null,"abstract":"The integration of artificial intelligence (AI), particularly generative AI, is transforming teacher professional development (PD) into a continuous, AI-mediated learning process. However, the effectiveness of AI-enhanced PD depends on teachers' readiness to engage with AI as a professional learning partner. This study develops and validates the preschool teachers' digital literacy scale as a diagnostic framework for assessing readiness for AI-enhanced PD among preschool teachers in China. Using data from 658 teachers nationwide, exploratory and confirmatory factor analyses supported a 5-D structure encompassing digital awareness, technical capability, pedagogical application, social responsibility, and PD orientation. Latent profile analysis identified three readiness groups—Emerging (13.37%), Progressing (46.20%), and Proficient (40.43%)—revealing a structural imbalance characterized by strong ethical awareness but comparatively weaker technological capability across profiles. The findings indicate that AI-enhanced PD should not be uniformly designed and instead requires differentiated, staged approaches aligned with teachers' readiness profiles. By positioning diagnostic profiling as an entry point for adaptive AI-supported PD design, this study offers scalable implications for early childhood education and AI-driven professional learning reform.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"19 ","pages":"255-270"},"PeriodicalIF":4.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147665453","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Three-Factor Model of Engagement and Persistence From Difficulty-Adjusted Practice Decisions in Online Mathematics Learning","authors":"Conrad Borchers;Kirk Vanacore;Markus W. H. Spitzer;Korbinian Moeller","doi":"10.1109/TLT.2026.3713651","DOIUrl":"https://doi.org/10.1109/TLT.2026.3713651","url":null,"abstract":"Engagement and persistence drive learning in online environments. Past research often proxied persistence with single, coarse engagement measures, such as time on task. However, recent research indicated more nuanced learner behaviors associated with productive and unproductive struggle. Here, we propose a longitudinal view based on log data in which engagement and persistence are expressed as repeated choices to start, continue, quit, or retry. Using two years of logs from <italic>bettermarks</i>, an online environment for learning mathematics (<italic>N</i>=2 129 students; >780 000 problem-set records), we estimated student propensities using Rasch-style models that adjust for content difficulty. By applying cross-validated factor analysis on propensities, reflecting decisions to start, continue, quit, and retry while working on problem sets, we identified three factors to predict future learning behavior. <italic>Completion propensity</i> predicts retrying and the selection of harder content despite lower accuracy; <italic>error-free completion</i> predicts higher first-attempt accuracy alongside a preference for easier content; and <italic>activity</i> predicts retry behavior while being associated with lower accuracy. The three-factor model explained substantially more variance than a unidimensional model in predicting future first-attempt accuracy (25% versus 3%, respectively) and student-chosen content easiness (18% versus 6%, respectively), although not retry behavior after failure. We discuss implications for effort-aware adaptivity and dashboards, contributing log-based indicators that can be computed for numerous online learning environments.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"19 ","pages":"804-817"},"PeriodicalIF":7.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11613197","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148781510","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analyzing Learning “in the Wild”: Modeling Individual Trajectories of Cognitive Engagement via Automated Text Classification and Social Network Analysis","authors":"Simon Krukowski;H. Ulrich Hoppe;Daniel Bodemer","doi":"10.1109/TLT.2026.3736330","DOIUrl":"https://doi.org/10.1109/TLT.2026.3736330","url":null,"abstract":"Online citizen science (CS) projects can be seen as informal learning communities where users “learn in the wild” about the topic at hand, yet assessing such learning through observational studies remains challenging due to the absence of explicit learning goals and formal assessment criteria. To address this, we propose a novel, theory-driven approach that approximates topic-specific learning as the longitudinal evolution of cognitive engagement based on the interactive, constructive, active, passive (ICAP) framework. For this, we fine-tuned a transformer-based language model (DeBERTa-V3-large) to automatically classify forum posts, applying it to a comprehensive dataset of 1.8 million posts across 30 online CS projects. Growth mixture modeling of 471 users with sustained forum activity over their first six months revealed that even among this active minority, the majority exhibited task-oriented routinization, while a small subgroup (8.1%) transitioned from lower to higher modes of cognitive engagement. Social network analysis further revealed that this increase in cognitive engagement is closely linked to social integration, with these users acquiring social capital and being sought out by others. Our findings demonstrate that combining natural language processing with network metrics can provide a scalable method for approximating learning processes in informal settings through cognitive engagement.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"19 ","pages":"962-978"},"PeriodicalIF":7.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11701420","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149188389","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Multifeature-Oriented Parallel Sequence Network for Classical Music Classification in Social-Emotional Learning","authors":"Shan-Ken Chien;Yu-Chi Chou;Pen-Chiang Chao;Hye Ran Park;Yuan-Jin Lin;Chih-Yun Chen;Po-Yung Hsiao;Meng-Xun Wu;Shih-Lun Chen;Kuo-Chen Li;Wei-Chen Tu","doi":"10.1109/TLT.2026.3733583","DOIUrl":"https://doi.org/10.1109/TLT.2026.3733583","url":null,"abstract":"With the rapid advancement of artificial intelligence, automated social-emotional music (SEM) classification has attracted increasing attention due to its practical applications in streaming platforms, education, and music therapy. However, existing models often suffer from low classification accuracy and limited generalization capability. This study proposes the multifeature-oriented parallel sequence network (MOPSNet), a multifeature fusion convolutional recurrent neural network designed for SEM classification in learning-oriented scenarios. MOPSNet integrates complementary music representations to capture both spectral and temporal emotional cues. These features are processed through a hybrid architecture that consists of parallel CNN branches for multiscale feature extraction and stacked bidirectional long short-term memory layers for modeling long-term temporal dependencies. In addition, multihead attention, residual connections, and skip connections are incorporated to preserve fine-grained temporal information and enhance training stability. To support robust learning, a data augmentation strategy is employed to enhance model generalization under conditions of limited and noisy data, which are common in educational music datasets. Experimental results on the SEM dataset demonstrate the effectiveness of MOPSNet, achieving an average accuracy of 95.05% with a standard deviation of 1% and a 95% confidence interval of [94.33%, 95.76%]. These findings confirm that MOPSNet offers an effective artificial intelligence based learning technology for supporting social-emotional learning through music, providing interpretable and reliable feedback in educational and special learning contexts.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"19 ","pages":"938-951"},"PeriodicalIF":7.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149188486","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Detection of Disengagement From Voluntary Quizzes: An Explainable Machine Learning Approach in Higher Distance Education","authors":"Behnam Parsaeifard;Christof Imhof;Tansu Pancar;Ioan-Sorin Comsa;Martin Hlosta;Nicole Bergamin;Per Bergamin","doi":"10.1109/TLT.2026.3668612","DOIUrl":"https://doi.org/10.1109/TLT.2026.3668612","url":null,"abstract":"Students disengaging from their tasks can have serious long-term consequences, including academic dropout. This is particularly relevant for students in distance education. One way to measure the level of disengagement in distance education is to observe participation in nonmandatory exercises in different online courses. In this article, we detect student disengagement in the nonmandatory quizzes of three reference courses with 42 instances distributed in four semesters from a distance-based university. We carefully identified the most informative student log data that could be extracted and processed from Moodle. Then, nine machine learning algorithms were trained and compared to obtain the highest possible prediction accuracy. Using the SHapley Additive exPlanations method, we developed an explainable machine learning framework that allows practitioners to better understand the decisions of the trained algorithm. The experimental results show a balanced accuracy of 91%, where about 85% of disengaged students were correctly detected. On top of the highly predictive performance and explainable framework, we provide a discussion on how to design a timely intervention to minimize disengagement from voluntary tasks in online learning.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"19 ","pages":"196-214"},"PeriodicalIF":4.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147558085","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Against Techno-Feudalism in Academia: Reclaiming Scholarly Autonomy in the Age of AI","authors":"Jin Yang;Jincheng Guo;Lili Gong","doi":"10.1109/TLT.2026.3673243","DOIUrl":"https://doi.org/10.1109/TLT.2026.3673243","url":null,"abstract":"Generative artificial intelligence, equipped with deep reasoning capabilities, is fundamentally reshaping academic research paradigms. Adopting the perspective of techno-feudalism, this study scrutinizes how digital platforms discipline and erode academic autonomy through mechanisms of data rent extraction, algorithmic behavioral steering, and entrenched path dependence. In response to this challenge, this article explores the potential foundations for maintaining the independence of human intelligence in an algorithmic age. We propose the concept of the “academic nomad” as an ideal subject archetype capable of navigating technology while maintaining a balance between human and machine intelligence. To reclaim academic autonomy, this research develops a synergistic framework for resistance encompassing macro-level institutional provision, meso-level transparent governance, and micro-level individual identity redemption. By establishing clear ethical boundaries for human–machine collaboration, ensuring equitable mechanisms for rights distribution, and enhancing the critical digital literacy of scholars, we aim to foster a new knowledge order grounded in technological negotiation rather than unilateral dependence.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"19 ","pages":"249-254"},"PeriodicalIF":4.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147665456","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Mixed-Methods Comparative Study of Remote and Traditional SDR Laboratories via Bloom’s Taxonomy, Surveys, and Focus Group","authors":"Rania Hussein;Zhiyun Zhang;Marcos Inoñan;Pablo Orduña","doi":"10.1109/TLT.2026.3681300","DOIUrl":"https://doi.org/10.1109/TLT.2026.3681300","url":null,"abstract":"Hands-on experimentation with software-defined radios (SDRs) is critical for teaching radio frequency and wireless communication concepts in electrical and computer engineering and computer science curricula. While traditional radios require costly hardware and have fixed configurations, SDRs offer a flexible, software-programmable alternative. Remote SDR laboratories further enhance accessibility by enabling students to conduct experiments anytime, anywhere—reducing institutional costs and offering flexibility. While SDR remote laboratories offer significant benefits, current research lacks systematic comparisons of their effectiveness in developing cognitive skills versus traditional labs and short-term skill persistence. This study evaluates the RHL-Remote Engineering Lab for Inclusive Access (RELIA), a novel SDR remote laboratory integrating popular hardware and software to support remote experimentation. A controlled split-group experiment was conducted with 36 students (primarily fourth-year undergraduates and graduate students with minimal communication theory background) in a capstone course at a public university in the United States. Lab 0 introduced foundational SDR skills, while Lab 1 compared learning outcomes between students using RHL-RELIA and traditional SDR lab kits. In Lab 2, all students used RHL-RELIA to assess short-term persistence. Student reports were evaluated using a Bloom’s taxonomy rubric spanning the Remember, Understand, Apply, Analyze, and Evaluate levels. Results revealed that the RHL-RELIA group outperformed the in-person cohort in Lab 1 across four cognitive domains (Remember, Understand, Analyze, and Evaluate). Longitudinal analysis of Lab 2 showed sustained gains: students who initially used RHL-RELIA retained higher performance in Remember, Understand, Apply, and Evaluate compared to the control group, suggesting long-term cognitive benefits. Pre- and postlab online surveys were administered to collect structured student feedback, complemented by a focus group study to gather qualitative insights into their learning experiences. Thematic analysis revealed positive perceptions of RHL-RELIA, with students emphasizing its usability and flexibility. These findings suggest that RHL-RELIA has advantages over traditional in-person SDR labs in fostering both immediate learning outcomes and short-term knowledge retention.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"19 ","pages":"462-479"},"PeriodicalIF":4.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11475572","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148003605","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Generative Agents for Learning Behavioral Simulation: An Interview-Driven and Multiexpert Reflection Framework","authors":"Cunling Bian;Zimeng Zhai;Saisai Ye;Weigang Lu","doi":"10.1109/TLT.2026.3692781","DOIUrl":"https://doi.org/10.1109/TLT.2026.3692781","url":null,"abstract":"Accurately modeling and predicting student learning behaviors remains a central challenge in educational research, as traditional approaches based on surveys or learning-process traces often struggle to capture the multidimensional and latent nature of learners' motivational and strategic states. Recent advances in large language models (LLMs) and generative agents offer new opportunities to simulate learning behaviors by integrating memory construction, contextual reasoning, and expert-informed reflection. In this study, we propose a theory-grounded framework for Learning Behavioral Simulation that leverages structured interview transcripts and multiexpert reflective modeling to instantiate generative student agents. We conducted interviews with 46 preparatory mathematics students and generated domain-specific reflections, spanning educational psychology, learning sciences, educational technology, assessment, and sociocultural education, using LLM-instantiated educational expert agents. The instantiated generative student agents, informed by these expert reflections, were tasked with predicting responses on the Motivated Strategies for Learning Questionnaire, enabling construct-level evaluation of motivational and learning strategy behaviors. Experimental results show that interview-driven agents augmented with expert reflections consistently outperform persona- and demographic-based baselines. Further analysis reveals that reflections from different expert domains capture complementary dimensions of learning behavior, improving both predictive robustness and interpretability. Overall, this work demonstrates how interview-grounded memory construction and expert-guided reflection can support interpretable, scalable, and model-agnostic generative simulation of student learning behaviors, with implications for personalized and explainable educational applications.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"19 ","pages":"520-534"},"PeriodicalIF":4.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148236171","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Telemetry-Enabled Driving Training Simulator for Autistic Learners in Community-Based Settings","authors":"Abigale Plunk;Mary Baker-Ericzen;Slomith Castellon;Elyse Simakaski;Dave Caudel;Nilanjan Sarkar","doi":"10.1109/TLT.2026.3708351","DOIUrl":"https://doi.org/10.1109/TLT.2026.3708351","url":null,"abstract":"Driving skill acquisition remains a significant barrier to independence for many autistic adolescents and young adults. Although driving simulators provide a safe environment for practice, most systems function primarily as stand-alone tools and evaluate performance using discrete error counts or short-term laboratory studies. This article presents a telemetry-enabled driving training framework that integrates immersive simulation, multimodal behavioral sensing, and facilitator-guided instruction. The platform captures continuous vehicle control inputs and gaze-based attention signals during simulation and transforms these data into behavioral indicators describing control stability, attentional allocation, and safety-relevant events. The system was deployed as part of a multiyear driving training program delivered across multiple community-based service settings serving a broader population of neurodivergent learners; however, the present analysis focuses specifically on 47 autistic participants who completed pre- and post-program simulator assessments. Pre–post comparisons showed reductions in speed variability, steering oscillation, and nongaze safety errors, indicating measurable simulator-based behavioral change within the driving simulator assessment context. These findings illustrate how telemetry-enabled simulation combined with facilitator-guided feedback can provide measurable insight into behavioral change during structured training. The system architecture also establishes a practical foundation for future adaptive and agentic artificial intelligence capabilities grounded in educator-supervised training contexts.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"19 ","pages":"648-662"},"PeriodicalIF":7.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11586012","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148626139","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dynamic Programming Techniques for Enhancing Cognitive Representation in Knowledge Tracing","authors":"Lixiang Xu;Xianwei Ding;Xin Yuan;Enhong Chen","doi":"10.1109/TLT.2026.3702387","DOIUrl":"https://doi.org/10.1109/TLT.2026.3702387","url":null,"abstract":"Knowledge tracing (KT) is a core task in intelligent education. It aims to dynamically track students’ knowledge mastery and predict their learning performance based on their historical answering records. Most of the existing mainstream methods focus on static feature enhancement while ignoring the interference of noncognitive noises, such as careless errors and random guesses. Moreover, current models cannot adaptively adjust cognitive representations according to learners’ individual differences. Therefore, it is necessary to consider the expressiveness of cognitive representations from the perspectives of students’ personalized answering performance and cognitive laws. To address these issues, this article proposes an adaptive cognitive representation orchestration knowledge tracing (AOCR-KT) model. Specifically, we design an adaptive cognitive optimization module. This module integrates answering status and question difficulty and introduces a <inline-formula><tex-math>$p$</tex-math></inline-formula>-mechanism involving interval performance and continuity rules to compensate for the subjective bias and inaccuracy caused by revising the status only from the perspective of difficulty. The relevant parameters are fed into the adaptive dynamic programming algorithm to judge and revise the coherence and continuity of the answering status, gradually minimize the cost function, and drive the answering status toward the optimal solution. In addition, we construct a partition optimization module. Considering the staged characteristics of learners’ cognitive development, the answering sequence is divided into multiple intervals according to individual differences, and each interval is optimized independently before global optimization. Finally, relation embeddings generated via bipartite graph modeling are fused with the optimized cognitive representations to further enhance cognitive expression. Extensive experiments on three large-scale public educational datasets demonstrate that the AOCR-KT model outperforms state-of-the-art KT models, which fully validates its effectiveness and superiority.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"19 ","pages":"679-693"},"PeriodicalIF":7.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148626857","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}