Your new experience awaits. Try the new design now and help us make it even better

ORIGINAL RESEARCH article

Front. Educ.

Sec. Higher Education

Volume 10 - 2025 | doi: 10.3389/feduc.2025.1649013

Machine learning-based multidimensional evaluation of the effectiveness of course civics teaching: a case study of the Occupational Health and Occupational Medicine course

Provisionally accepted
Zhanyue  ZhengZhanyue ZhengCheng  KangCheng KangChengqiang  WangChengqiang WangYou  LiYou LiYan  SunYan Sun*
  • Guilin Medical University, Guilin, China

The final, formatted version of the article will be published soon.

This study investigated the outcomes of integrating Course-based Ideological and Political Education (CIPE) into Occupational Health and Occupational Medicine (OHOM) courses within the "Internet Plus" context. A total of 230 questionnaires were distributed to senior undergraduate students at Guilin Medical University, with 220 valid responses collected, yielding a 95.6% response rate. Data analysis was conducted using Python 3.11 and R 4.1.1, incorporating descriptive statistics, t-tests/non-parametric tests, chi-square tests, and multiple linear regression while controlling for confounding factors such as gender and age. The machine learning component employed XGBoost, random forests, and support vector regression (SVR), combined with five-fold cross-validation and SHAP analysis for model optimisation and interpretation. Results showed that students in the CIPE-integrated group achieved significantly higher composite scores (83.90 ± 3.08) compared with the traditional group (82.66 ± 4.28, p < 0.05). Regression analysis identified course returns (β = 0.54, 95% CI: 0.16–0.92), group participation (β = 0.44, 95% CI: 0.03– 0.84), online resource utilisation (β = 0.46, 95% CI: 0.05–0.87), and ethical benefits (β = 0.52, 95% CI: 0.12 – 0.92) as significant predictors of performance. SHAP analysis further highlighted the critical roles of group participation, course motivation, 2 ethical benefits, and note review in model predictions, while also revealing individual differences in learning behaviours and value formation. In conclusion, the deep integration of CIPE into OHOM courses through blended teaching significantly enhanced students ' academic performance, professional ethics, and social responsibility. The combined use of traditional statistical methods and interpretable machine learning provides robust, data-driven evidence for evaluating educational interventions and offers methodological guidance for extending CIPE applications within preventive medicine and public health curricula.

Keywords: Ideological and political education, higher education, OccupationalHealth and Occupational Medicine, Educational innovation, machine learning

Received: 18 Jun 2025; Accepted: 04 Sep 2025.

Copyright: © 2025 Zheng, Kang, Wang, Li and Sun. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence: Yan Sun, Guilin Medical University, Guilin, China

Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.