Talk · International Conference on Intelligent Sustainable Systems · March 12, 2025

Insights into Mental Health Challenges in Digital Education using Suitable Machine Learning Techniques

K. P. S. Saketh, Hitesh Kumar S., Palgun Kumar Reddy P, C. Jyotsna, Aiswariya Milan K

Abstract

The growth in online learning has brought into focus its potential impact on the mental health of students. The research employs machine learning techniques to examine how mental health is influenced by the digital environments of education. By using a dataset that contains several indicators of mental health estimates and classify different models such as Random Forests, Decision tree, Support Vector Machines (SVM), K-Nearest Neighbors Classifier (KNN), Gradient boosting, Multi-Layer Perceptron (MLP), Bagging, Boosting, Stacking, Logistic Regression, and Naive Bayes to predict the status of student’s mental health based on their responses. Model accuracy and reliability are enhanced through rigorous data preprocessing, such as outlier removal and feature selection. The findings indicate that the Decision Tree classifier performs best in predicting mental health impacts, achieving 75% accuracy and an F-score of 82.7%. The research emphasizes the importance of understanding mental health implications associated with internet-based learning and provides insights for developing effective interventions for promoting student well-being.

Online Learning and AnalyticsArtificial Intelligence in HealthcareStudent Stress and Copingstudent mental healthonline learningdigital education

Insights into Mental Health Challenges in Digital Education using Suitable Machine Learning Techniques

Abstract

More by Jyotsna Chandrasekharan