A Chatbot Model for Enhancing Mental Health-Seeking Behavior
Main Article Content
Abstract
Mental health disorders remain significantly under-addressed among women in low-resource settings due to stigma, lack of awareness, limited access, and high treatment costs. To address this gap, this study proposes an AI-powered chatbot model designed to support mental health-seeking behavior. The solution integrates a rule-based natural language processing (NLP) system, with machine learning (ML) algorithms for mood classification and adaptive response delivery. The model was developed using two publicly available mental health datasets sourced from Kaggle and tested with 71 pregnant and lactating women at Mandera County, Kenya. Natural language features were processed using TF-IDF, and user moods were predicted using the HistGradientBoostingClassifier. The chatbot's modular architecture includes an emotional intelligence layer, a behavioral intervention engine, and a triage and referral system. Evaluation results showed high classification accuracy of 0.99 and strong user engagement and satisfaction. Furthermore, a key innovation in the model is its two-tiered web user interface, which includes both text-based interaction and appointment booking functionality. This integration not only facilitates access to mental health resources and referrals but also plays a critical role in reducing stigma and enhancing confidentiality. By allowing users to engage anonymously and schedule appointments discreetly, the system fosters a sense of safety and comfort, encouraging individuals who might otherwise avoid seeking help due to societal judgment. These findings highlight the role of digital AI tools in expanding mental health access in underserved populations. Collaboration with psychologists further validated the model's clinical relevance. These findings imply that policymakers, healthcare providers, and community health workers should adopt and integrate AI-powered chatbots into maternal health services to expand access, reduce stigma, and strengthen mental health-seeking behaviour in underserved populations.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
I/We agree to transfer the copyright of this manuscript to the International Journal of Professional Practice (The IJPP) in the event that the manuscript is published in the Journal.
I/We give the undersigned authors of the manuscript have made the following declaration:
(a) That I/We have made substantial contribution during the conception and design, or acquisition of data, or analysis and interpretation of the data,
(b) That I/We have participated in drafting the article or revising it critically for important intellectual content,
(c) That I/We have read and confirm the content of the manuscript and have agreed to it,
(d) That I/We have participated sufficiently in the work to take public responsibility for appropriate portions of the content of the paper,
(e) That I/We give guarantee that the content of the manuscript is original, and has not beenvpublished elsewhere and is not currently being considered for publication by another journal.
