STM Journals Peer-reviewed research from Consortium e-Learning Network

Research & Reviews: A Journal of Embedded System & Applications Review Article

Depression Detection Using AI with Chatbot Support

  1. S. A. Patil Department of Computer Technology, Sanjivani K.B.P. Polytechnic, Kopargaon
  2. Anushka Sanjay Gaikwad Department of Computer Technology, Sanjivani K.B.P. Polytechnic, Kopargaon
  3. Komal Ashok Gaikwad Department of Computer Technology, Sanjivani K.B.P. Polytechnic, Kopargaon
  4. Sampada Nitin Aher Department of Computer Technology, Sanjivani K.B.P. Polytechnic, Kopargaon
  5. Sakshi Babasaheb Mogal Department of Computer Technology, Sanjivani K.B.P. Polytechnic, Kopargaon

Abstract

Depression is a major global health concern and a significant contributor to suicide rates worldwide. India reports a high number of suicide cases, making the early detection of mental distress and depression essential for timely intervention. This research presents an AI-based system for depression detection that integrates deep learning, natural language processing (NLP), and a chatbot for user support. The system analyzes facial expressions using convolutional neural networks (CNNs) and assesses emotional states from textual input through machine-learning techniques such as Naïve Bayes and support vector machines (SVMs). The system captures real-time facial images through a camera, which are then processed using CNN algorithms and classified into emotional categories such as happy or sad. Simultaneously, it analyzes users' language patterns to evaluate sentiment, stress levels, and depressive tendencies. To address class imbalance, the study employs the synthetic minority over-sampling technique (SMOTE), thereby improving the accuracy of depression detection. In addition, the system incorporates a chatbot interface that interacts with users, providing support and personalized recommendations based on the detected emotional state. The model was evaluated using datasets such as DAIC-WOZ and PHQ-8 and demonstrated strong performance in identifying depressive symptoms. The integration of facial-expression analysis and text-based sentiment assessment provides a comprehensive approach to depression detection, enhancing the accuracy and reliability of the diagnostic process.

Keywords

References (16)

  1. Stone LB, Veksler AE. Stop talking about it already! Co-ruminating and social media focused on COVID-19 was associated with heightened state anxiety, depressive symptoms, and perceived changes in health anxiety during Spring 2020. BMC Psychology. 2022;10(1). doi:10.1186/s40359-022-00734-7
  2. Chancellor S, Baumer EPS, De Choudhury M. Who is the "Human" in Human-Centered Machine Learning. Proceedings of the ACM on Human-Computer Interaction. 2019;3(CSCW):1-32. doi:10.1145/3359249
  3. Mikolov T, Chen K, Corrado G, Dean J. Efficient estimation of word representations in vector space [preprint]. 2013. arXiv:1301.3781. doi:10.48550/arXiv.1301.3781.
  4. Guntuku SC, Yaden DB, Kern ML, Ungar LH, Eichstaedt JC. Detecting depression and mental illness on social media: an integrative review. Current Opinion in Behavioral Sciences. 2017;18:43-49. doi:10.1016/j.cobeha.2017.07.005
  5. Mancini G, Agnoli S, Baldaro B, Ricci Bitti PE, Surcinelli P. Facial Expressions of Emotions: Recognition Accuracy and Affective Reactions During Late Childhood. The Journal of Psychology. 2013;147(6):599-617. doi:10.1080/00223980.2012.727891
  6. Guarnera M, Hichy Z, Cascio MI, Carrubba S. Facial Expressions and Ability to Recognize Emotions From Eyes or Mouth in Children. Europe’s Journal of Psychology. 2015;11(2):183-196. doi:10.5964/ejop.v11i2.890
  7. Hey T, Butler K, Jackson S, Thiyagalingam J. Machine learning and big scientific data. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences. 2020;378(2166):20190054. doi:10.1098/rsta.2019.0054
  8. Sen S, Raghunathan A. Approximate Computing for Long Short Term Memory (LSTM) Neural Networks. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. 2018;37(11):2266-2276. doi:10.1109/tcad.2018.2858362
  9. Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, et al. Attention is all you need. In: Guyon I, Von Luxburg U, Bengio S, Wallach H, Fergus R, Vishwanathan S, et al., editors. Advances in Neural Information Processing Systems 30 (NIPS 2017). Red Hook (NY): Curran Associates, Inc.; 2017. p. 5998–6008. doi:10.48550/arXiv.1706.03762.
  10. Rabasco A, Corcoran V, Andover M. Alone but not lonely: The relationship between COVID-19 social factors, loneliness, depression, and suicidal ideation. PLOS ONE. 2021;16(12):e0261867. doi:10.1371/journal.pone.0261867
  11. Song K, Tan X, Qin T, Lu J, Liu TY. MPNet: masked and permuted pre-training for language understanding [preprint]. 2020. arXiv:2004.09297. doi:10.48550/arXiv.2004.09297.
  12. Liu B. Sentiment Analysis and Opinion Mining. Synthesis Lectures on Human Language Technologies. 2012. doi:10.1007/978-3-031-02145-9
  13. Schuller BW, Batliner AM. Computational Paralinguistics. 2013. doi:10.1002/9781118706664
  14. Yang Z, Dai Z, Yang Y, Carbonell J, Salakhutdinov R, Le QV. XLNet: generalized autoregressive pretraining for language understanding [preprint. 2019. arXiv:1906.08237. doi:10.48550/arXiv.1906.08237.
  15. Poria S, Cambria E, Bajpai R, Hussain A. A review of affective computing: From unimodal analysis to multimodal fusion. Information Fusion. 2017;37:98-125. doi:10.1016/j.inffus.2017.02.003
  16. Yeasmin S, Das S, Afroj T, Suha SH, Prabha M, Vanu N, et al. Artificial Intelligence in Mental Health: Leveraging Machine Learning for Diagnosis, Therapy, and Emotional Well-being. Journal of Ecohumanism. 2025;4(3). doi:10.62754/joe.v4i3.6640
Support