Copyright © 2025 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{167278,
        author = {PILLALAMARRI VEENA and KATROTH BALAKRISHNA MARUTHIRAM},
        title = {Unveiling Chronic Stress: A Social Media Perspective Using Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {3},
        pages = {733-739},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=167278},
        abstract = {Stress is a universal experience, manifesting in two forms: acute and chronic. Acute stress arising briefly from events like traffic jams or disagreements, is a natural part of daily life, enhancing our stress response system’s vigilance. In contrast, chronic stress results from prolonged exposure to diverse stressors, straining the body’s normal functioning and contributing to severe health issues such as heart disease and mental disorders. Recognizing the influence of social media, researchers have explored novel ways to identify chronic stress in users. They compiled data from 971 individuals facing chronic stress, analyzing 54,546 social media posts from Sina microblog between July 5, 2018, and December 1, 2019. The study introduced innovative techniques: A specialized stress-oriented word embedding to enhance sensitivity in detecting stress-related expressions and a sophisticated multi-attention model capturing post interconnections, accurately inferring long-term stress levels and categories. Results were remarkable, with an 80.65% accuracy in detecting category-aware stress levels. 86.49% accuracy in identifying chronic stress levels, and an outstanding 93.07% accuracy in pinpointing chronic stress categories. This pioneering approach not only illuminates the pervasive issue of chronic stress in the digital age but also offers a robust methodology for precise identification, paving the way for targeted interventions and support systems for those grappling with chronic stress.},
        keywords = {Chronic stress detection, social media, attention mechanism.},
        month = {August},
        }