An Empirical Comparison of Machine Learning Models for Student’s Mental Health Illness Assessment

• DOI: 10.24203/ajcis.v10i1.6882
• Publication Date: 2022-02-27T15:49:58Z
• Authors: Prathamesh Muzumdar; Ganga Prasad Basyal; Piyush Vyas
• Keywords: Gradient boosting; Empirical Research

Student’s mental health problems have been explored previously in higher education literature various contexts including empirical work involving quantitative and qualitative methods. Nevertheless, comparatively few research could be found, aiming for computational methods that learn information directly from data without relying on set parameters a predetermined equation as an analytical method. This study aims to investigate the performance of Machine learning (ML) models used education. ML considered are Naïve Bayes, Support Vector Machine, K-Nearest Neighbor, Logistic Regression, Stochastic Gradient Descent, Decision Tree, Random Forest, XGBoost (Extreme Boosting Tree), NGBoost (Natural) algorithm. Considering factors illness among students, we follow three phases processing: segmentation, feature extraction, classification. We evaluate these against classification metrics such accuracy, precision, recall, F1 score, predicted run time. The analysis includes two contributions: 1. It examines survey-based educational dataset, inferring significant by tree-based algorithm; 2. explores importance [variables] datasets infer social support, environment, childhood adversities student’s illness.