Wearable sensor technology is increasingly being integrated into educational settings, offering innovative approaches to enhance teaching and learning experiences. These devices track various physiological and environmental variables, providing valuable insights into student engagement, comprehension, and educational environments. However, the extensive and continuous data streams generated by these sensors create significant challenges for learning analytics. This paper presents a comprehensive review of research on learning analytics incorporating wearable technology, systematically identifying methods and approaches that address wearable sensor data challenges. We begin with a systematic review of wearable sensor technologies’ historical development and the current state of sensor data in learning analytics. We then examine multimodal sensor applications in learning analytics and propose research and application trends aligned with educational development needs. Our analysis identifies three key challenges: ethical considerations, explainable learning analytics, and technological and data management issues. The paper concludes by outlining seven future development directions for wearable sensors in educational contexts.

This study investigates the creators, effects, and inhibitors of technostress among STEM teachers, addressing a critical yet underexplored issue in the digitalization of education. Grounded in the technostress model and the job demands–resources (JD-R) model, the study examines the relationships among technostress creators, burnout, organizational effects (job satisfaction, organizational commitment, and work performance), and technostress inhibitors. A cross-sectional survey was conducted with 378 STEM teachers from Zhejiang Province, China. Structural equation modeling (SEM) was employed to test the hypothesized paths. The results revealed that technostress creators significantly increased teacher burnout and negatively affected organizational commitment and work performance. Burnout mediated the impact of technostress creators on job satisfaction and organizational commitment. Technostress inhibitors were found to alleviate burnout, mitigate technostress creators, and enhance STEM teachers’ commitment. These findings validate the applicability of the technostress model in the context of K–12 STEM education in China and highlight the importance of organizational mechanisms for supporting teacher well-being and performance. The study contributes to both theory and practice by proposing an integrative model of technostress and offering actionable recommendations for school leadership to effectively manage technostress.

Utilizing big data and artificial intelligence technologies, we developed the Collaborative Structure Search Framework (CSSF) algorithm to analyze students’ learning paths from real-world data to determine the optimal sequence of learning knowledge components. This study enhances sustainability and balance in education by identifying students’ learning paths. This allows teachers and intelligent systems to understand students’ strengths and weaknesses, thereby providing personalized teaching plans and improving educational outcomes. Identifying causal relationships within knowledge structures helps teachers pinpoint and address learning issues, forming the basis for adaptive learning systems. Using real educational datasets, the research introduces a multi-sub-population collaborative search mechanism to enhance search efficiency by maintaining individual-level superiority, population-level diversity, and solution-set simplicity across sub-populations. A bidirectional feedback mechanism is implemented to discern high-quality and low-quality edges within the knowledge graph. Oversampling high-quality edges and undersampling low-quality edges address optimization challenges in Learning Path Recognition (LPR) due to edge sparsity. The proposed Collaborative Structural Search Framework (CSSF) effectively uncovers relationships within knowledge structures. Experimental validations on real-world datasets show CSSF’s effectiveness, with a 14.41% improvement in F1-score over benchmark algorithms on a dataset of 116 knowledge structures. The algorithm helps teachers identify the root causes of students’ errors, enabling more effective educational strategies, thus enhancing educational quality and learning outcomes. Intelligent education systems can better adapt to individual student needs, providing personalized learning resources, facilitating a positive learning cycle, and promoting sustainable education development.

The deployment of large language models (LLMs) in academic paper evaluation is increasingly widespread, yet their trustworthiness remains debated; to expose fundamental flaws often masked under conventional testing, this study employed extreme-scenario testing to systematically probe the lower performance boundaries of LLMs in assessing the scientific validity and logical coherence of papers from the humanities and social sciences (HSS). Through a highly credible quasi-experiment, 40 high-quality Chinese papers from philosophy, sociology, education, and psychology were selected, for which domain experts created versions with implanted “scientific flaws” and “logical flaws”. Three representative LLMs (GPT-4, DeepSeek, and Doubao) were evaluated against a baseline of 24 doctoral candidates, following a protocol progressing from ‘broad’ to ‘targeted’ prompts. Key findings reveal poor evaluation consistency, with significantly low intra-rater and inter-rater reliability for the LLMs, and limited flaw detection capability, as all models failed to distinguish between original and flawed papers under broad prompts, unlike human evaluators; although targeted prompts improved detection, LLM performance remained substantially inferior, particularly in tasks requiring deep empirical insight and logical reasoning. The study proposes that LLMs operate on a fundamentally different “task decomposition-semantic understanding” mechanism, relying on limited text extraction and shallow semantic comparison rather than the human process of “worldscape reconstruction → meaning construction and critique”, resulting in a critical inability to assess argumentative plausibility and logical coherence. It concludes that current LLMs possess fundamental limitations in evaluations requiring depth and critical thinking, are not reliable independent evaluators, and that over-trusting them carries substantial risks, necessitating rational human-AI collaborative frameworks, enhanced model adaptation through downstream alignment techniques like prompt engineering and fine-tuning, and improvements in general capabilities such as logical reasoning.

1. Educational assessment in higher education not only serves to measure learning outcomes but also exerts a profound influence on instructional decision-making, student learning behaviors, and edu...