Mind Harbor: Development of an AI-Powered Prototype for Student Mental Health Support
DOI:
https://doi.org/10.3991/ijim.v20i12.62164Keywords:
AI-powered mental health support, Large Language Models (LLMs), University student well-being, Human-centered design, Chatbot-based interventionAbstract
This paper presents the development of a prototype for a system called Mind Harbor; an AI-based platform aimed at supporting the mental health of university students. It builds on our earlier study, Mind Harbor: Navigating Wellness Together—with AI Integration, which identified the need for socially sensitive and accessible mental health support in Oman. In this second phase, we move from concept to implementation. The system uses a chatbot powered by a large language model (LLM) to provide empathetic and context-aware conversations with students. The prototype follows human-centered design principles to ensure it feels supportive and non-judgmental. It includes a simple web and mobile interface, basic privacy through username-and-password login, and culturally adapted responses. The system architecture has four main layers: user interface, application layer, LLM integration, and data management with MongoDB. Features such as a mood tracker, guided prompts, and a crisis support button are included to make the platform more useful and safer. While the system is still in its early stage, this paper provides details of the design, development, and integration process. It also outlines privacy safeguards, limitations, and planned improvements. The prototype serves as a foundation for future testing, expert review, and stronger security features.
References
[1] Thomas, et.al, 2024,. Mind Harbor: Navigating Wellness Together – with AI Integration. ISSN: 2096-3246 Volume 56, Issue 09, September, 2024
[2] Dosovitsky, G., Pineda, B. S., Jacobson, N. C., Chang, C., Escoredo, M., & Bunge, E. L. (2020). Artificial intelligence chatbot for depression: Descriptive study of usage. JMIR Formative Research, 4(11), e17065.
[3] Fulmer, R., Joerin, A., Gentile, B., Lakerink, L., & Rauws, M. (2018). Using psychological artificial intelligence (Tess) to relieve symptoms of depression and anxiety: Randomized controlled trial. JMIR Mental Health, 5(4), e64.
[4] Gaffney, H., Mansell, W., Edwards, R., Wright, J., & McDonald, B. (2023). Conversational agents in mental health care: A systematic review. Digital Health, 9, 20552076231165748.
[5] Inkster, B., Sarda, S., & Subramanian, V. (2018). An empathy-driven, conversational artificial intelligence agent (Wysa) for digital mental well-being: Real-world data evaluation. JMIR mHealth and uHealth, 6(11), e12106.
[6] Silva, B., & Tesfagiorgis, Y. G. (2023). Large Language Models as an Interface to Interact with API Tools in Natural Language. Linnaeus University.
[7] Tosic, D. (2023). Artificial intelligence-driven web development and agile project management using OpenAI API and GPT technology (Bachelor’s thesis, Mid Sweden University).
[8] Ekin, S. (2023). Prompt engineering for ChatGPT: A quick guide to techniques, tips, and best practices. TechRxiv. https://doi.org/10.36227/techrxiv.22683919.v1
[9] Guo, Z., Lai, A., Thygesen, J. H., Farrington, J., Keen, T., & Li, K. (2024). Large language models for mental health applications: Systematic review. JMIR Mental Health, 11, e57400. https://doi.org/10.2196/57400
[10] Hua, Y., Na, H., Li, Z., Liu, F., Fang, X., Clifton, D., & Torous, J. (2025). A scoping review of large language models for generative tasks in mental health care. npj Digital Medicine, 8(230). https://doi.org/10.1038/s41746-025-01611-4
[11] Rickwood, D., Deane, F. P., Wilson, C. J., & Ciarrochi, J. (2007). Young people’s help-seeking for mental health problems. Australian e-Journal for the Advancement of Mental Health, 4(3), 218–251.
[12] Tandon, A., van Kessel, R., Hall, J. L., Al-Taie, N., McGuinness, C., & O’Leary, F. (2023). Human factors, usability, and human-centered design in sensor-based digital health technologies: A scoping review. npj Digital Medicine, 6(1), 115.
[13] Vaidyam AN, Wisniewski H, Halamka JD, Kashavan MS, Torous JB. Chatbots and Conversational Agents in Mental Health: A Review of the Psychiatric Landscape. The Canadian Journal of Psychiatry. 2019;64(7):456-464. doi:10.1177/0706743719828977
[14] Hosseini, S. E., Pervez, S., Manalo, P. L., Iqbal, M. J., Shahbaz, M. (2026). Depression Prediction Using Enhanced Machine Learning Pipeline. International Journal of Online and Biomedical Engineering (iJOE), 22(1), pp. 147–163
[15] Ayodele, A., Adetunla, A., Akinlabi, E. (2025). Depression Severity Prediction Using Stacked Heterogenous Learning on Integrated Biomedical and Lifestyle Data. International Journal of Online and Biomedical Engineering (iJOE), 21(14), pp. 156–167
[16] Angotti, M.A. (2025). Rethinking Youth Mental Health: Challenges, Interventions, and Cultural Perspectives. Journal for Future Society and Education (JFSE), 2(2), pp. 29–40.
[17] Ajlouni, A. O., Almahaireh, A. S., & Whaba, F. A.-A. (2023). Students’ Perception of Using ChatGPT in Counseling and Mental Health Education: The Benefits and Challenges. International Journal of Emerging Technologies in Learning (iJET), 18(20), 199–218. https://doi.org/10.3991/ijet.v18i20.42075
[18] Ajlouni, A., AlOmary, A., Wahba, F. A.-A., Al-Kubaisi, H., & Ibrahim, A. (2025). The Intensity of Using ChatGPT in Relation to Academic Stress: A Cross-Sectional Study. International Journal of Interactive Mobile Technologies (iJIM), 19(17), 81–100. https://doi.org/10.3991/ijim.v19i17.56495
[19] Alajmi, A., et al. (2025). Artificial Intelligence and Mental Health: Bibliometric Analysis. International Journal of Interactive Mobile Technologies (iJIM). https://doi.org/10.3991/ijim.v19iXX.58041
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Sherin Thomas, Jaishree Devi, Marwa Said Amur Al Khuitari, Ramesh Palanisamy
This work is licensed under a Creative Commons Attribution 4.0 International License.
