The Double-Edged Sword of Social Media: An Analysis of Its Contribution to Stress via Anxiety and Loneliness

Keshav Kanda , Sandeep Ranjan

Mental Health Prediction, Fuzzy Logic, Random Forest, Decision Support, Machine learning.

Prediction of multi-level mental health status has been a central objective of contemporary data-driven psychiatry, especially because digitalization, technostress, and social pressures are aggravating the burden of depression and its associated disorders. Based on fuzzy-machine-learning methodologies, this work develops a Fuzzy-Optimized Multi-Level Random Forest framework to establish an interpretable decision-support model for classifying mental health into graded risk tiers. Using carefully curated datasets that integrate self-reported symptoms, behavioral biomarkers, and contextual stressors, the developed system begins with rigorous preprocessing and feature selection from the input space. It is followed by the application of fuzzy logic to encode expert knowledge as linguistic variables and rules, which tune the key ensemble parameters before final prediction. In experimental evaluation, the fuzzy-enhanced ensemble evidences high accuracy, sensitivity, specificity, and F1 score, demonstrating its robust performance under uncertainty while maintaining transparency in its decision pathways. Thus, the presented research provides a comprehensive framework that integrates psychological theory, fuzzy inference, and ensemble learning for supporting early detection, risk stratification, and informed intervention within mental health.

Published Paper   E-Certificate

"The Double-Edged Sword of Social Media: An Analysis of Its Contribution to Stress via Anxiety and Loneliness", IJSDR - International Journal of Scientific Development and Research (www.IJSDR.org), ISSN:2455-2631, Vol.11, Issue 1, page no.a191-a208, January-2026, Available :https://ijsdr.org/papers/IJSDR2601024.pdf

Volume 11 Issue 1, January-2026

Pages : a191-a208

Paper Reg. ID: IJSDR_306748

Published Paper Id: IJSDR2601024

Downloads: 000327

Research Area: Science and Technology

Country: Phagwara/Kapurthala, Punjab, India

Published Paper PDF: https://ijsdr.org/papers/IJSDR2601024

Published Paper URL: https://ijsdr.org/viewpaperforall?paper=IJSDR2601024

ISSN: 2455-2631 | IMPACT FACTOR: 9.15 Calculated By Google Scholar | ESTD YEAR: 2016

An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 9.15 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator

Publisher: IJSDR(IJ Publication) Janvi Wave

This work is licensed under a Creative Commons Attribution 4.0 International License and The Open Definition