Research on the optimization algorithm of college mental health education strategy based on big data in the new quality productivity environment

Read full text Summarise with VIRAT
Authors: Wei Zhang, Qianru Shi, Duanhe Li
Cited by: 0
References: 24

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This paper proposes an improved RS-ID3 algorithm based on rough set theory and continuous attribute discretization method. Taking the students of 2022 class in a higher education institution as the research object, the mental health data were collected. Data mining was performed on the mental health test data, and a mental health prediction model was built. The predictive performance of the model was evaluated, and an obsessive-compulsive symptom decision-making model was built using the optimized RS-ID3 algorithm to explore the students' mental health. The results showed that the decision tree prediction accuracy using the RS-ID3 algorithm was 8.5 percentage points higher than that using the ID3 algorithm, and the mining rules indicated that students who were not from two-parent families were more likely to have obsessive-compulsive symptoms. The mining results of the combined two algorithms were fed back to the counselors, providing a theoretical basis for the evaluation and intervention of college students' mental health status.

Fields of Study & Subjects

Data Mining and Machine Learning Applications Artificial Intelligence in Healthcare Educational Technology and Pedagogy

Publication details

Journal / source
Journal of Network and Innovative Computing
Volume
14
Pages
16–16
Publication date
25 March 2026
Language
EN