Authors : G.Gangadevi; Sudharsun Ravisankar; Vikash P

Volume/Issue : Volume 10 - 2025, Issue 8 - August

Google Scholar : https://tinyurl.com/3u7c88ef

Scribd : https://tinyurl.com/bdexnzz6

DOI : https://doi.org/10.38124/ijisrt/25aug508

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 30 to 40 days to display the article.

Abstract : "With growing concerns about mental well-being, users want efficacious means to monitor emotions and get personalized assistance, with current solutions often sacrificing privacy or offering shallow revelations. ZenLoop overcomes the shortcomings by combining AI-based analysis of emotion with safe Web3 storage to provide both well-being support alongside privacy. This paper builds a conversational AI chatbot that offers coping mechanisms, a mood tracker to record emotion states, and an analysis dashboard to enable users to identify behavior patterns. Developed with React for frontend, Node.js for backend, and MongoDB for organized data, ZenLoop provides empathy-based responses leveraging NLP models trained on mental well-being dialogues. Journals are encrypted and stored in Web3-based storage, with immutable, decentralized protection. Trends in moods are depicted in interactive graphs, and AI-driven insights enable users to monitor emotion shifts. Tests show enhanced user engagement, improved self-perception, along with superior protection of data. The chatbot is effective in detecting levels of distress along with recommended interventions, promoting emotional resilience. By combining AI-driven tools for mental well-being with the security of blockchain, ZenLoop enables users to express emotion securely, monitor their mental well-being patterns, and get personalized advice at no cost of privacy. This work demonstrates the potential of privacy-based AI-based solutions to promote well-being at the emotional level, leading to the development of secure, user-centric applications for mental well-being.

Keywords : AI-Powered Chatbot, Journal Entry, Natural Language Processing (NLP), Mental Health Support, Emotion Analysis, Mood Tracking, user Privacy, Data Encryption, Personalized Coping Strategies, Real-Time Analytics, Behavior, Secure Data Storage, Sentiment Analysis, Interactive Dashboard, Socket.io Real-Time Communication, Open-Source AI Models.

References :

1. S. Hamdoun, R. Monteleone, T. Bookman and K. Michael, "AI-Based and Digital Mental Health Apps: Balancing Need and Risk," in IEEE Technology and Society Magazine, vol. 42, no. 1, pp. 25-36, March 2023, doi: 10.1109/MTS.2023.3241309.
2. S. Allen, "Improving Psychotherapy With AI: From the Couch to the Keyboard," in IEEE Pulse, vol. 13, no. 5, pp. 2-8, Sept. Oct. 2022, doi: 10.1109/MPULS.2022.3208809.
3. Y. Cai, D. Lin and Q. Lu, "Comparison of Different Machine Learning Algorithms in the Mental Health Assessment of College Students," in Journal of ICT Standardization, vol. 12, no. 4, pp. 409-427, December 2024, doi: 10.13052/jicts2245-800X.1243.
4. H. Mazumdar, C. Chakraborty, M. Sathvik, s. Mukhopadhyay and P. K. Panigrahi, "GPTFX: A Novel GPT-3 Based Framework for Mental Health Detection and Explanations," in IEEE Journal of Biomedical and Health Informatics, doi: 10.1109/JBHI.2023.3328350
5. A. -M. Bucur, A. -C. Moldovan, K. Parvatikar, M. Zampieri, A. R. KhudaBukhsh and L. P. Dinu, "On the State of NLP Approaches to Modeling Depression in Social Media: A Post-COVID-19 Outlook," in IEEE Journal of Biomedical and Health Informatics, doi: 10.1109/JBHI.2025.3540507
6. M. Neary and S. M. Schueller, “State of the field of mental health apps,” Cogn. Behav. Pract., vol. 25, no. 4, pp. 531–537, Nov. 2018.
7. Vuyyuru, T. L. Praveena, A. Sharma, M. Yelagandula and S. Nelli, "Mental Health Therapist Chatbot Using NLP," 2024 International Conference on Artificial Intelligence and Quantum Computation-Based Sensor Application (ICAIQSA), Nagpur, India, 2024, pp. 1-6, doi: 10.1109/ICAIQSA64000.2024.10882362
8. National Institute of Mental Health, “Technology and the future of mental health treatment.” Accessed: Jun. 20, 2021. [Online]. Available: https://www.nimh.nih.gov/ health/topics/technology-and-the-future-of-mentalhealth-treatment/
9. E. Anthes, “Pocket psychiatry: Mobile mental-health apps have exploded onto the market, but few have been thoroughly tested,” Nature, vol. 532, no. 7597, pp. 20–24, 2016.
10. Youper, “Mental health care created with you,” youper. ai, San Francisco, CA, USA, 2021. [Online]. Available: https://www.youper.ai/
11. P. Gooding and T. Kariotis, “Mental health apps are not keeping your data safe,” Scientific American, Nov. 15, 2022. [Online]. Available: https://www.scientificamerican.com/article/mental-health-apps-arenot-keeping-your-data-safe/
12. Kang, B., & Hong, M. (2025). Development and Evaluation of a Mental Health Chatbot Using ChatGPT 4.0: Mixed Methods User Experience Study With Korean Users. JMIR Medical Informatics, 13, e63538. doi:10.2196/63538.
13. Fan, X., Yang, L., Wang, X., Lyu, D., & Chen, H. (2025). Constructing a Knowledge-Guided Mental Health Chatbot with LLMs. In Proceedings of the 16th Asian Conference on Machine Learning (pp. 287–302). PMLR.
14. Banerjee, S., Agarwal, A., Ghosh, P., & Bar, A. K. (2024). Boosting Workplace Well-Being: A Novel Approach with a Mental Health Chatbot for Employee Engagement and Satisfaction. American Journal of Artificial Intelligence, 8(1).
15. MindLumen. (2024). Top 6 AI Apps for Mental Health in 2024: A New Era of Digital Support. MindLumen Blog.