Currently submitted to: JMIR Research Protocols
Date Submitted: Sep 4, 2026
Open Peer Review Period: Sep 8, 2026 - Nov 3, 2026
(currently open for review)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Development and Feasibility Testing of a Prototype AI-Chatbot to Deliver Personalised Psychoeducation on Depression, Anxiety, and Alcohol Use among University Students in South Africa: Protocol for a Mixed-Methods Study
ABSTRACT
Background:
Depression, anxiety, and alcohol use remain the most common mental health conditions among university students. Yet, about 8 in 10 students diagnosed with mental illness go untreated due to stigma, poor mental health literacy, and limited knowledge of available support services in South Africa. AI-chatbots offer a scalable solution to deliver accessible, personalised psychoeducation. However, most existing chatbots have been designed for high-income contexts, with limited cultural adaption for low resource settings and use beyond clinical settings.
Objective:
The study aims to (1) determine the effects of psychoeducational interventions on individual mental health literacy and alcohol literacy constructs among young adults aged 18-30 years; (2) Describe literacy levels and its predictive factors among university students; (3) develop and validate an AI-chatbot for personalised psychoeducation; and (4) assess the feasibility and acceptability of the AI-chatbot for personalised psychoeducation. The goal is to evaluate the use of AI-chatbot to deliver personalised psychoeducation to university students in South Africa.
Methods:
This protocol uses a mixed-methods design with four sub-studies. First, we will conduct evidence synthesis of existing psychoeducational interventions for mental health literacy and alcohol literacy. Secondly, a cross-sectional survey will be used to describe mental health literacy and alcohol literacy levels and identify predictors of literacy levels. Thirdly, we will co-develop culturally appropriate psychoeducation content for fine-tuning an AI-chatbot. Finally, we will assess acceptability of the developed chatbot.
Results:
All four sub-studies have been approved by Wits Human Research Ethics Committee (M25/07/02). We have made substantial progress in sub-study 1 and 2. We have completed literature search, screening and data extraction and data synthesis is ongoing for sub-study 1. Data collection for sub-study 2 commenced on May 13, 2026, and still ongoing. A total of 441 respondents has completed the survey to date.
Conclusions:
This study will co-produce an AI-chatbot to deliver personalised psychoeducation to students. The findings will provide evidence on the ethical adaptation of artificial intelligence for mental health promotion as well as offer a low-cost, accessible platform to deliver mental health education to university students.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.