PREDICTING AND UNDERSTANDING UNIVERSITY STUDENT MENTAL HEALTH

Abstract

The mental health challenges faced by college students are increasing across the globe and impact their academic performance, social well-being and future productivity. This study introduces a machine learning-based predictive model for identifying students at risk of mental health disorders such as depression, anxiety, and stress. Survey based and behavioral datasets were used to evaluate multiple supervised learning algorithms such as Random Forest, Support Vector Machine (SVM), Logistic Regression and Artificial Neural Networks (ANN). The analysis incorporates data augmentation strategies, tackles class imbalance using SMOTE (Synthetic Minority Over-sampling Technique), The study involved data preprocessing, feature selection, model training, and evaluation using metrics like accuracy, F1-score, and ROC-AUC over 5-fold cross-validation.