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{185225,
        author = {Priyanshu and Sarthak Mittal and Sanchit Vasdev},
        title = {Depression Detection on Twitter using Machine Learning Approaches},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {5},
        pages = {824-829},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=185225},
        abstract = {Social media networks like Facebook, Twitter, and Instagram have reshaped how individuals interact and shape their digital identities. While these platforms offer significant benefits for communication and fostering communities, a correlation has been observed between their extensive use and a rise in depression cases. The early identification of such mental health challenges is critical because timely intervention can dramatically enhance a person's well-being. This research investigates the application of machine learning methods to detect indicators of depression among Twitter users through an analysis of their tweets and network activity. To capture significant linguistic cues, the data was pre-processed using a variety of natural language processing techniques, such as tokenization, the removal of stop-words, and word embedding. On a dataset comprising both random and depressive tweets, classifiers including TF-IDF and Long Short-Term Memory (LSTM) were trained and assessed, showing proficient performance in differentiating between users. The results indicate that more comprehensive feature sets enhance detection precision and that specific language patterns—especially those conveying sadness, anxiety, or anger—are powerful predictors of depression. Beyond the technical outcomes, this research emphasizes how AI-powered tools can supplement conventional mental health services by providing scalable, readily available, and proactive monitoring solutions. With further development, these methods could address existing gaps in mental health care, facilitate timely support for individuals, and foster healthier online environments.},
        keywords = {},
        month = {October},
        }