ORIGINAL RESEARCH article
Front. Psychol.
Sec. Educational Psychology
Students' Stress Prediction and Explainable Analysis Based on Improved Decision Trees
Provisionally accepted
Cheng Liu*
Shuang Yu- Jiangsu Vocational Institute of Commerce, Nanjing, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Nowadays students are burdened with pressures from various aspects such as academics, social life, and career planning. It is of great significance to accurately predict their stress levels and analyze the key influencing factors. This study constructs a predictive model for adolescents and young adult students stress by leveraging an enhanced decision tree (DT) algorithm. By comparing nine machine learning algorithms including logistic regression (LR) and DT, it was found that the DT performed outstandingly in predicting students' stress, with an accuracy rate of 0.909. Furthermore, intelligent optimization algorithms such as the harris hawks optimization (HHO) algorithm were used to optimize the DT model. The final accuracy rate of the HHO-DT model reached 0.927, with the fewest misclassified samples. With the help of the shapley additive explanations (SHAP) model, the impact of various features on the prediction of students' stress levels was analyzed, and the important roles of features such as blood pressure, social support, and depression were clarified. The research results provide a scientific and effective basis for intervention measures taken by college mental health educators, parents, and students themselves, which is helpful to relieve students' stress and promote their physical and mental health.
Keywords: Student Stress Prediction, Decision tree algorithm, Harris hawks optimization, SHAP model, machine learning
Received: 13 Aug 2025; Accepted: 27 Nov 2025.
Copyright: © 2025 Liu and Yu. 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: Cheng Liu
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.