Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{191223,
        author = {K. Gowtham and S. Shirley},
        title = {A MACHINE LEARNING–BASED APPROACH FOR STRESS PREDICTION FROM SOCIAL MEDIA TEXT USING NATURAL LANGUAGE PROCESSING},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {6762-6765},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=191223},
        abstract = {The digital revolution has dramatically reshaped human interaction, with social media platforms becoming central to communication, self-expression, and emotional sharing. While these platforms offer unprecedented connectivity and access to information, they have simultaneously intensified psychological challenges such as stress, anxiety, depression, and emotional exhaustion. Individuals frequently disclose their emotional states indirectly through text-based content such as posts, comments, and discussions. These digital traces provide valuable insights into mental well-being, yet manual analysis of such large-scale unstructured data is impractical and inefficient.
This research presents an advanced Social Media Stress Prediction System that leverages machine learning (ML) and natural language processing (NLP) techniques to automatically detect stress indicators from textual data. The system follows a structured pipeline involving text preprocessing, feature extraction, supervised model training, and performance evaluation using a benchmark stress-labeled dataset. A web-based application is developed to deploy the trained model and provide real-time stress prediction through a user-friendly interface. Experimental results indicate that the proposed system achieves reliable accuracy and demonstrates robustness in identifying stress-related linguistic patterns. This work highlights the potential of artificial intelligence as a scalable and objective tool for early stress detection, mental health monitoring, and psychological research.},
        keywords = {Social Media Stress, Machine Learning, Natural Language Processing, Mental Health Monitoring, Text Classification, Stress Detection},
        month = {January},
        }