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{195779,
        author = {Bankuru Yashwanth and Pagadala Srinivasu and Chatla Tejesh Reddy and Billa Ganesh Venkateswara Sai and Gollu Ramalakshmi},
        title = {Automated Depression Detection from Social Media Using Deep Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {1165-1170},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195779},
        abstract = {Mental health conditions, particularly clinical depression, have emerged as a significant global health crisis, affecting millions of individuals across diverse demographics. In the digital era, social media platforms have become primary venues for self-expression, offering a unique "digital phenotype" of a user's psychological state. This research focuses on identifying depression through the automated analysis of social media text data using state-of-the-art deep learning architectures. We implement and evaluate four hybrid models: BERT combined with Convolutional Neural Networks (CNN), DistilBERT with Bidirectional Long Short-Term Memory (BiLSTM), DeBERTa with BiLSTM, and DistilGPT2 paired with BiLSTM. The methodology encompasses rigorous data cleaning, tokenization using model-specific vocabularies, and the extraction of high-dimensional contextual embeddings. Our experimental results, analyzed through detailed confusion matrices, demonstrate that these models significantly outperform traditional machine learning techniques by capturing subtle semantic and temporal patterns in text. The final system is deployed via a Flask-based web application, providing an accessible and scalable tool for early mental health screening and monitoring.},
        keywords = {Mental Health, Depression Detection, Social Media Analytics, Deep Learning, Transformers, BERT, BiLSTM, Natural Language Processing (NLP), Flask.},
        month = {April},
        }