Home / Archives / July 2026 / Articles

AN INTELLIGENT WEB-BASED STUDENT MENTAL HEALTH PREDICTION SYSTEM USING SUPPORT VECTOR MACHINE ALGORITHM

Authors: Gurana Hareesh, Dr. A. Mary Sowjanya, Varsha Kumari

Country: India

Abstract

Recognizing the onset of mental health issues in students early is vital to supporting students’ psychological health and success. In this project, a machine learning based framework for automatic prediction of the Mental health status of students from a structured questionnaire is proposed. The system gathers answers concerning a number of mental and behavioural factors, that include sleep top quality, stress, solitude, college pressures, sadness, concentration, workout routines, smoking, liquor usage, and more. These become pre-processed by Categorical Encoding and feature scaling before being analysed by a Support Vector Machine (SVM) Classifier. The trained model classifies students into three mental health classes: Healthy, Moderate and High Risk and also provides chrome personalized recommendations for positive mental health practices. The experimental results show that the proposed SVM model with a high prediction accuracy of 98.32% is effective in identifying students who may need psychological assistance. Interfacing of developed system with web application using flask gives them a secure users authentication, history of assessments, monitoring of administrators, generating reports etc. making them capable of use in real world scenarios in the field of education. Overall, the proposed method is shown to be viable in the implementation of an intelligent, scalable and user friendly mental health screening system that could aid in implementing early intervention, informed decision making and proactive management of student mental health.

Keywords

Student Mental Health, Machine Learning, Support Vector Machine (SVM), Questionnaire Based Assessment, Flask, Mental Health Prediction.

References

1) CH. Raga Madhuri, M. Srinu, J. S. K. Bandaru, and G. M. A. Vardhan, “AI-Powered Mental Health
Screening and Support for Homeless Children,” in 2025 AI-Driven Smart Healthcare for Society 5.0,
Kolkata, India, Feb. 14–15, 2025, pp. 115–120, IEEE, doi: 10.1109/IEEECONF64992.2025.10963316.
2) J. Virani, M. Shukla, N. Daredi, P. Shah, and A. Bhanushali, “Mental Healthcare Analysis using Power
BI & Machine Learning,” in 2023 4th International Conference on Signal Processing and
Communication (ICSPC), Coimbatore, India, Mar. 2023, pp. 73–76, IEEE, doi:
10.1109/ICSPC57692.2023.10125680 .
3) M. Karunakaran, J. Balusamy, and K. Selvaraj, “Machine Learning Models based Mental Health
Detection,” in 2022 Third International Conference on Intelligent Computing, Instrumentation and
Control Technologies (ICICICT), Kannur, India, 2022, pp. 835–842, IEEE, doi:
10.1109/ICICICT54557.2022.9917622.
4) X. Lin, "A Machine Learning-Based Mental Health Monitoring and Early Warning System for College
Students," Journal of Sensors, vol. 2022, Article ID 3828677, 2022.
[https://doi.org/10.1155/2022/3828677](https://doi.org/10.1155/2022/3828677)
5) C. K. Archanaa and R. Gnanajeyaraman, "Interpretable Multimodal Prediction of Student Mental Health
Deterioration Using TabNet-Based Deep Learning," in 2025 IEEE 9th International Conference on
Information and Communication Technology (CICT), 2025, doi: 10.1109/CICT67193.2025.11399215.
6) M. Karunakaran, J. Balusamy, and K. Selvaraj, "Machine Learning Models based Mental Health
Detection," in 2022 Third International Conference on Intelligent Computing, Instrumentation and
Control Technologies (ICICICT), 2022, pp. 835–842, doi: 10.1109/ICICICT54557.2022.9917622.
7) M. Sen, R. Rajkumar, and J. Masih, "Student Stress Patterns: A Data Driven Exploration using Machine
Learning Amidst Academic Challenges and Health Impacts," in 2024 ASU International Conference in
Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS), IEEE, 2024, pp. 1294–
1298, doi: 10.1109/ICETSIS61505.2024.10459468.
8) N. Sharma, I. S. Patel, N. K. Singh, and B. K. Mishra, "Predictive Modelling of Mental Health Disorders
Using Machine Learning Classifiers," in *2024 International Conference on Artificial Intelligence and
Quantum Computation-Based Sensor Application (ICAIQSA)*, IEEE, 2024.