learning analytics

This study addresses a critical limitation in current learning analytics tools, wherein frequency-oriented visualizations often obscure rare yet educationally significant student feedback. To bridge the gap between quantitative visualization and qualitative educational research, the authors engaged STEM education researchers in analyzing student logs using the WordStream platform. Through an integrated approach combining thematic analysis, member checking, and mixed-methods user research, the study uncovered epistemological tensions educators face when repurposing quantitative codings for qualitative inquiry. Three core themes emerged: tool experience, disciplinary contextualization, and the integration of quantitative and qualitative paradigms. Building on these insights, the work proposes design principles for visualizations that support deep qualitative exploration, offering both theoretical grounding and practical guidance for the next generation of learning analytics tools.

This study addresses the lack of reusable, cross-context data analytics infrastructure in current educational AI systems, which hinders consistent processing of heterogeneous learning interaction data. Building upon the A4L modular data architecture, the authors design and implement a domain-agnostic, highly configurable analytics pipeline that unifies the collection, processing, and analysis of multi-source educational AI interaction data. Through modular design, an extensible architecture, and cross-domain data integration techniques, the pipeline supports closed-loop personalized learning and instructional feedback. Its generalizability, scalability, and reusability are empirically validated by successfully reproducing key analytical results across three distinct educational settings, thereby providing foundational support for the evaluation and iterative improvement of educational AI systems.

This work addresses the lack of fine-grained, quantitative assessment of learning processes and code quality in current programming education, which hinders accurate diagnosis of students’ comprehension and instructional efficacy. The authors propose a plugin system integrated into mainstream code editors that, for the first time, adapts industrial-grade development log analysis to educational contexts. By continuously capturing students’ coding behaviors, error messages, and progress data in real time, the system constructs a timestamp-driven behavioral tracking model to derive quantitative metrics. This approach enables structured recording and analysis of programming activities, facilitating timely evaluation of instructional content, identification of common learning bottlenecks, and the creation of an open programming behavior database tailored for educational research and personalized learning.

To address subjectivity, high labor costs, and insufficient cultural adaptation in classroom observation, this study develops the first multimodal AI behavioral analysis system tailored for Asian classrooms. Methodologically, it integrates audio, video, and environmental sensor data; proposes a culturally adaptive educational AI analytics framework; designs a scoring-free, feedback-oriented instructional reflection dashboard; and establishes the first publicly available audiovisual annotation dataset of Asian classroom interactions. Key contributions include: (1) introducing interpretable, behavior-based classroom metrics; (2) achieving real-time behavioral recognition with low cognitive load and high usability—validated by eight experts from Singapore’s National Institute of Education; and (3) significantly reducing human effort required for classroom observation. The system provides teachers with objective, scalable, and context-sensitive technological support for professional development.

Learning analytics often suffers from low user trust and intervention acceptance due to opaque reasoning processes. To address this, we propose a novel “transparency-through-exploration” paradigm, developed via iterative human-centered design (n=15), resulting in a self-service metric editor that enables end-users—particularly instructors—to interactively construct, inspect, and refine analytical metrics. This tool grants users direct agency over both the logic and generation process of learning metrics. Empirical evaluation demonstrates significant improvements in system transparency, user trust, satisfaction, and adoption willingness. Our key contribution is the first systematic integration of exploratory metric construction into learning analytics practice, shifting transparency from post-hoc explanation to real-time, participatory engagement through an operationalizable tool design. This advances human-centered, trustworthy, and usable learning analytics.

Traditional log-based metrics struggle to capture learners’ affective-cognitive states, limiting comprehensive explanations of learning outcomes. This study addresses this gap by integrating trait-like Deep Effortless Concentration (DEC)—a dispositional form of flow—with fine-grained reading strategy behaviors extracted from e-book interactions to construct a more holistic engagement metric. Through questionnaire-based DEC assessment, detailed analysis of reading logs, and regression modeling, the research reveals, for the first time, DEC’s moderating role in the relationship between behavioral indicators and academic performance. Findings show that incorporating DEC and reading strategies explains an additional 21.3% of the variance in academic achievement beyond baseline models, offering both theoretical and methodological innovations for personalized learning analytics.

Educational video design in higher education lacks data-driven optimization tools and open resources, hindering learning effectiveness. To address this, we propose the first open-source, scalable video analytics workflow integrating multimodal feature extraction (frames, audio, transcripts), structured metadata modeling, and supervised machine learning—including regression and feature importance analysis—to enable evidence-informed design iteration. We release the first community-curated, open database of educational video attributes. Empirical validation across two engineering courses identified key pedagogical factors—such as lecture pacing and visual complexity—and informed 12 pedagogical experiments and three international collaborative projects. Our framework establishes a reproducible, generalizable paradigm for optimizing educational video design through empirical, multimodal analysis.

Learning analytics dashboards often lack interpretability, hindering students’ self-regulated learning and metacognitive development. Method: This study proposes a large language model (LLM)-based natural language explanation generation method to enhance dashboard interpretability. Through an empirical comparative experiment, LLM-generated skill-state interpretations and personalized learning recommendations were evaluated by domain experts alongside teacher-crafted explanations and a no-explanation baseline. Contribution/Results: This work presents the first systematic validation in educational technology demonstrating that LLM-generated explanations significantly outperform baselines in pedagogical appropriateness, comprehensibility, and practical utility—particularly in diagnostic accuracy, recommendation feasibility, and overall educational value—as rated by education experts. Findings confirm that expert-guided LLMs serve as reliable tools for improving dashboard explainability and pedagogical support. The study establishes a novel paradigm for explainable AI in learning analytics, advancing both theoretical understanding and practical implementation of interpretable educational technologies.

This study aims to enhance the support provided by immersive teacher simulation training for pre-service teachers’ professional decision-making and reflective practice. By integrating an extended reality (XR) platform with multimodal learning analytics—including verbal discourse, behavioral logs, and eye-tracking data—the research systematically employs multimodal data as a mediating tool to visualize the teaching reasoning process and uncover the cognitive distribution and sequential interaction patterns embedded in instructional discourse. The work advances beyond descriptive observation toward predictive modeling, identifying prototypical patterns of teacher–student interaction. These findings offer both theoretical grounding and empirical evidence for the development of scalable, data-driven next-generation teacher education environments.

This study addresses the lack of systematic preprocessing standards, integrated analytical workflows, and cross-method consistency checks in current computer-based assessment process data. To bridge this gap, the authors propose an end-to-end analytical framework featuring a unified preprocessing pipeline and a dual-path analysis paradigm that synergistically combines feature engineering with model-based inference. The framework incorporates large language models (LLMs) to standardize action sequences and facilitate process-data-driven differential item functioning (DIF) detection. Technically, it integrates timestamp correction, action chunking, n-gram and TF-IDF feature extraction, multidimensional scaling, hidden Markov modeling, and subtask identification. Empirical results demonstrate that n-gram–based behavioral clustering offers diagnostic value for incorrect responders, multidimensional scaling effectively reconstructs behavioral constructs, and process data can identify and mitigate construct-irrelevant group differences.