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 (Preprint)

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.