Exploring students' cognitive abilities has long been an important topic in education. This study employs data-driven artificial intelligence (AI) models supported by explainability algorithms and PSM causal inference to investigate the factors influencing students' cognitive abilities, and it delved into the differences that arise when using various explainability AI algorithms to analyze educational data mining models. In this paper, five AI models were used to model educational data. Subsequently, four interpretable algorithms, including feature importance, Morris Sensitivity, SHAP, and LIME, were used to globally interpret the results, and PSM causal tests were performed on the factors that affect students' cognitive abilities. The results reveal that self-perception and parental expectations have a certain impact on students' cognitive abilities, as indicated by all algorithms. Our work also uncovers that different explainability algorithms exhibit varying preferences and inclinations when interpreting the model, as evidenced by discrepancies in the top ten features highlighted by each algorithm. Morris Sensitivity presents a more balanced perspective, while SHAP and feature importance reflect the diversity of interpretable algorithms, and LIME shows a unique perspective. This detailed observation highlights the practical contribution of interpretable AI algorithms in the field of educational data mining, paving the way for more refined applications and deeper insights in future research.

In the era of educational digital transformation, integrating information and communication technology (ICT) into school administration aligns with the goals of promoting personalized learning, equity, and teaching quality. This study examines how ICT reshapes management practices, addresses challenges, and achieves educational objectives. To explore ICT’s impact on school administration (2009–2024), we conducted a systematic scoping review of four databases (Web of Science, Scopus, ScienceDirect, and IEEE Xplore) following the PRISMA-ScR guidelines. Retrieved studies were screened, analyzed, and synthesized to identify key trends and challenges. The results show that ICT significantly improves administrative efficiency. Automated systems streamline routine tasks, allowing administrators to allocate more time to strategic planning. It enables data-driven decision-making. By analyzing large datasets, ICT helps identify trends in student performance and resource utilization, facilitating accurate forecasting and better resource allocation. Moreover, ICT strengthens stakeholder communication. Online platforms enable instant interaction among teachers, students, and parents, increasing the transparency and responsiveness of school administration. However, there are challenges. Data privacy concerns can erode trust, as student and staff data collection and use may lead to breaches. Infrastructure deficiencies, such as unreliable internet and outdated equipment, impede implementation. The digital divide exacerbates inequality, with under-resourced schools struggling to utilize ICT fully. ICT is vital in educational administration. Its integration requires a strategic approach. This study offers insights for optimizing educational management via ICT and highlights the need for equitable technological advancement to create an inclusive, high-quality educational system.

Background: In the digital age, safeguarding children’s mental health (CMH) has emerged as one of the most pressing challenges. The rapid evolution of social media (SM) from a basic networking platform to a multifaceted tool has introduced numerous conveniences. However, it has also posed significant challenges to children’s mental well-being. Methods: Given the intricate relationship between the widespread use of SM and mental health issues in children, this study conducted a systematic scoping review to examine the literature on the impact of SM on CMH from 2014 to 2024. Literature searches were performed across five databases (Web of Science, ScienceDirect, Scopus, PubMed, and APA PsycInfo), and the retrieved studies were screened, extracted, and analyzed by the Preferred Reporting Items for Systematic Reviews and Meta-Analysis Extension for Scoping Review (PRISMA-ScR) guidelines. Results: The review identified a complex relationship between SM use and CMH. Different SM platforms exhibited varying effects on children. Frequent SM use was strongly associated with lower self-esteem, depressive symptoms, anxiety, and other mental health challenges in children. Conversely, moderate use of SM facilitated social interactions and emotional expression, which may have a positive influence on mental health. Additionally, factors such as social support from family and school were found to play a critical role in mitigating the negative effects of SM on CMH. Conclusions: To enhance CMH, it is essential to guide children in the appropriate use of SM, promote awareness of privacy protection, and ensure adequate family and social support. Future research should further investigate the specific mechanisms underlying SM use and its differential effects on children across varying age groups and regions.

Large Language Models (LLMs) are driving a revolution in the way we access information, yet there remains a lack of exploration to capture people’s information interaction preferences in LLM environments. In this study, we designed a comprehensive analysis framework to evaluate students’ prompt texts during a professional academic writing task. The framework includes a dimensionality reduction and classification method, three topic modeling approaches, namely BERTopic, BoW-LDA, and TF-IDF-NMF, and a set of evaluation criteria. These criteria assess both the semantic quality of topic content and the structural quality of clustering. Using this framework, we analyzed 288 prompt texts to identify key topics that reflect students’ information interaction behaviors. The results showed that students with low academic performance tend to focus on structural clarity and task execution, including task inquiry, format specifications, and methodological search, indicating that their interaction mode is instruction-oriented. In contrast, students with high academic performance interact with LLM not only in basic task completion but also in knowledge integration and the pursuit of novel ideas. This is reflected in more complex topic levels and diverse, innovative keywords. It shows that they have stronger self-planning and self-regulation abilities. This study provides a new approach to studying the interaction between students and LLM in engineering education by using natural language processing to process prompts, contributing to the exploration of the performance of students with different performance levels in professional academic writing using LLM.

Public health education (PHE) plays a crucial role in mitigating the impact of public health crises, particularly in the context of high-density and aging populations. This study aims to address the challenges posed by these demographic trends in community public service spaces (CPSSs) by integrating geospatial and population data. Using bivariate spatial autocorrelation analysis, this research investigates the relationship between PHE and social determinants of health across 40 CPSSs in Macao. Additionally, it highlights the underutilization of digital technologies (DTs) in PHE. A non-participatory, short-term field survey and observational study were conducted to analyze PHE data quantitatively and descriptively in Macao’s CPSSs. Moran’s I and LISA index were used to test spatial autocorrelation at 90% and 99% confidence levels. The results revealed significant positive spatial correlations between the distribution of community public service institutions (CPSIs) and the population in southern Macao, as well as between the elderly population and PHE themes and formats. PHE topics predominantly focus on health/fitness, geriatrics, chronic diseases, and mental health. Despite this, PHE remains heavily reliant on offline formats, with limited integration of DTs. Challenges such as low digital literacy and limited acceptance of DTs among community workers and the public hinder their broader adoption. This study provides valuable insights for optimizing the allocation of health education resources in densely populated and aging urban areas, offering both practical recommendations and theoretical support for health policy making and implementation.

Inquiry-based learning (IBL) is a problem-driven and exploration-centred learning method. The emergence of large language models (LLMs) such as ChatGPT provides a new interactive environment for IBL. However, research has not sufficiently explored how students interact with LLMs for IBL. This study aimed to understand students’ behaviours interacting with LLM at different cognitive levels during the IBL process. We conducted an experiment on a data science academic writing task and used Bloom’s educational taxonomy to examine the behavioural patterns of students’ IBL at different cognitive stages. Through the exploratory thematic analysis of 117 interview transcripts, 370 interaction records and 1,694 minutes of screen recordings, we identified 14 interaction patterns among students at different levels of prior knowledge. This article discusses the potential impact of self-efficacy and metacognitive monitoring on students’ learning behaviour in an LLM-driven learning environment and called for the design of a guiding planning framework and scaffolding to address challenges such as reliance on artificial intelligence. Our study provides new insights for the development of IBL in the era of emerging artificial intelligence technologies. Implications for practice or policy: Educators can improve student inquiry-based learning outcomes by designing cognitive scaffolding that targets specific higher-order thinking stages. Instructional designers should develop planning frameworks that mitigate over-reliance on artificial intelligence while fostering student metacognitive monitoring. Policymakers could implement training programmes to enhance students' critical evaluation skills within an LLM-driven environment.