International Journal of Scientific Research and Engineering Development

The very fast growth in the use of social media among students is a serious cause for concern regarding its effect on their mental health. This research investigates the association between specific usages of social media and psychological distress among students within the age bracket of 17-23 years. We followed a quantitative cross-sectional design, wherein we integrated survey data on behavioral, temporal, and lifestyle factors with predictive modeling-Logistic Regression, Random Forest, and Multi-Layer Perceptron. The aim was the identification of key predictors of high mental distress. The research findings revealed that the increased use of the medium, particularly at night, and the consumption of the content had a dominant effect in the increased levels of anxiety, emotional exhaustion, and depression. The best model of the RF algorithm correlated well and achieved high F1 Scores (0.79).Late-night usage was identified through the AUC figures of 0.84, confirming the negative effects when the use of the medium was high and predominantly at night. The research conclusions imply the multifaceted function of the impacts of the use of the medium and the role of well-planned and well-executed wellness programs and mental health support systems currently and in the future to reduce the impacts and individual risks.

Zameel Subhaan, Sonali Karale, Athul Sobin, Nikhil Saju,"Impact of Social Media on Student Mental Health Using Deep Learning" International Journal of Scientific Research and Engineering Development, V9(3): Page(1784-1789) May-June 2026. ISSN: 2581-7175. www.ijsred.com. Published by Scientific and Academic Research Publishing.