design teacher-facing analytics

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.

This study addresses the challenge of interpreting and applying eye-tracking data in English Language Arts (ELA) instruction. We designed and implemented a teacher-centered gaze analytics dashboard that integrates user-centered design and data storytelling principles, employing hierarchical visualizations and narrative scaffolding to render eye-movement data pedagogically meaningful. The dashboard incorporates a large language model (LLM)-driven conversational AI agent enabling natural-language interaction and multimodal learning analytics. Our key contribution is the first translation of raw eye-tracking metrics into actionable, narrative-driven instructional insights—significantly reducing teachers’ cognitive load through LLM-mediated interpretation. Empirical evaluation demonstrates that the tool substantially improves teachers’ efficiency in inferring students’ cognitive states and classroom engagement, alleviates the burden of data interpretation, and enhances the quality of formative assessment and pedagogical decision-making—thereby validating the feasibility and educational value of gaze analytics in authentic teaching contexts.

This study investigates how K–12 mathematics teachers allocate limited real-time instructional support based on students’ prior help-seeking history and current engagement, and evaluates the cross-lesson learning effects of such support. Integrating teacher interviews with large-scale interaction data from the MATHia intelligent tutoring system, the research employs mixed-effects models, cross-lagged panel analysis, and additive factor models to reveal a “stickiness” in teacher attention: students who previously received help are more likely to be supported again. Although this targeted intervention significantly enhances immediate lesson performance, it shows no significant predictive effect on skill mastery in subsequent lessons. These findings offer empirical evidence for optimizing teacher attention allocation and advancing educational equity.

Current learning analytics dashboards (LADs) overemphasize data visualization while neglecting core cognitive processes—such as meaning-making and self-regulation—thereby limiting their effectiveness in supporting learners’ active engagement. To address this, we propose AUF, a learner-centered dynamic learning analytics framework. AUF introduces a novel multidimensional coupling model that integrates context awareness, dynamic meaning-making, adaptive feedback, and embedded metacognitive support, emphasizing real-time interactivity among components and personalized evolutionary trajectories. The framework is operationalized through four synergistic mechanisms: contextual modeling, a sensemaking strategy engine, an adaptive mechanism, and metacognitive prompting techniques. Our work yields a scalable theoretical framework and empirically grounded design principles. It provides both methodological guidance and empirical evidence for developing learning analytics tools that are more effective, equitable, and engaging—advancing the field beyond static, instructor-oriented dashboards toward truly learner-empowering systems.

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 ambiguity in K–12 teachers’ understanding of data literacy, which hinders their ability to design assessments that effectively capture its core components—particularly in the application of data visualization. Through interviews with 13 teachers and drawing on theories from data visualization, human-computer interaction, and the learning sciences, the research systematically identifies four central challenges in assessing data literacy: conceptual confusion, lack of authentic context, misalignment of tools, and insufficient disciplinary integration. Building on these findings, the study proposes actionable assessment design strategies that integrate real-world contexts with subject-specific learning goals. This work offers interdisciplinary theoretical grounding and practical guidance to support educators in implementing effective data literacy instruction.

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 study addresses the scarcity of large-scale, teacher-centered empirical research in Indonesia, which has hindered the development of localized AI-in-education systems and policies. Through a nationwide survey of 349 K–12 teachers, it offers the first systematic investigation—grounded in teachers’ perspectives—into the current use, needs, and barriers related to AI applications in lesson preparation, content generation, and media production. Integrating quantitative analysis with multidimensional indicators, the findings reveal significant disparities in AI adoption: primary school teachers exhibit more consistent usage, while educators in eastern regions report higher acceptance. Key constraints include suboptimal generic output quality, inadequate infrastructure, and insufficient localization. The study underscores how geographic region, educational level, and teaching experience shape AI uptake, highlighting the critical role of contextual adaptation in effectively implementing AI in educational settings.

This study addresses the challenge teachers face in highly heterogeneous classrooms when attempting to simultaneously account for students’ academic performance, motivational states, and specific learning needs—such as dyslexia or attention deficits—in delivering differentiated instruction. To this end, we propose the first teacher-in-the-loop multi-agent AI framework that unifies modeling of motivation, academic achievement, and learning differences. The framework comprises four coordinated agents: learner simulation, diagnostic assessment, instructional material generation, and efficacy evaluation, all designed to support teacher-led differentiated instruction. Integrating multi-agent systems, learner modeling, generative AI, and human-AI collaboration, the system demonstrated high practical utility in evaluations by 70 K–12 in-service teachers, while needs-validation workshops with 30 school principals further confirmed its urgency and feasibility in real-world educational settings.