The Impact of Digital Technology Use on Teaching Quality in University Physical Education: An Interpretable Machine Learning Approach
Applied Sciences · 09.07.2025 · 15 (14) · 7689
DOI: 10.3390/app15147689 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 09.07.2025. Verfasst von Liguo Zhang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shandong Humanities and Social Sciences Project.
Abstract (Originalsprache)
Amid the ongoing digital transformation of higher education, increasing attention has been paid to the impact of digital technologies on teaching quality—particularly in physical education settings that require high levels of interaction and physical engagement. This study examined 1158 university students across China using a cross-sectional design, integrating interpretable machine learning models with structural equation modeling to systematically assess how the frequency of use of seven common digital technologies influences teaching quality in physical education classes. The study also investigated the mediating roles of perceived teacher support and academic self-efficacy. Nine machine learning models and logistic regression analyses were conducted to predict teaching quality, employing feature permutation importance and SHapley Additive exPlanations (SHAP) to evaluate the relative contribution of each digital tool. Results identified multimedia courseware, e-textbooks, and question banks as the most influential predictors of teaching quality. The SHAP analysis further revealed that management software, educational websites, and multimedia materials had significant positive effects and exhibited synergistic interactions in improving teaching outcomes. Structural equation modeling showed that digital technology use had a significant direct positive effect on teaching quality (B = 0.347, p < 0.001). Moreover, perceived teacher support and academic self-efficacy not only served as independent mediators (95% CI = [0.146, 0.226], p < 0.001; 95% CI = [0.024, 0.063], p < 0.001) but also functioned as a chain mediating effect (95% CI = [0.036, 0.083], p < 0.001). This study is the first to integrate interpretable machine learning with structural modeling to elucidate the mechanisms through which digital technologies influence teaching quality in university-level physical education. The findings underscore the critical mediating roles of teacher support and student self-efficacy, providing both theoretical contributions and practical implications for enhancing digital pedagogy in higher education.
Förderung
- Shandong Humanities and Social Sciences Project
Zitieren
APA
Zhang, L., Liu, Z., Zhao, L., & Gao, J. (2025). The Impact of Digital Technology Use on Teaching Quality in University Physical Education: An Interpretable Machine Learning Approach. Applied Sciences, 15(14), 7689. https://doi.org/10.3390/app15147689
Vancouver
Zhang L, Liu Z, Zhao L, Gao J. The Impact of Digital Technology Use on Teaching Quality in University Physical Education: An Interpretable Machine Learning Approach. Applied Sciences. 2025;15(14):7689. doi:10.3390/app15147689
BibTeX
@article{Zhang2025,
author = {Zhang, Liguo and Liu, Zetan and Zhao, Liangyu and Gao, Jiarui},
title = {The Impact of Digital Technology Use on Teaching Quality in University Physical Education: An Interpretable Machine Learning Approach},
journal = {Applied Sciences},
year = {2025},
volume = {15},
number = {14},
pages = {7689},
doi = {10.3390/app15147689}
}
EUVIMED