Design, development, and evaluation of STI Shield: A multi-chatbot mobile application for sexual health education and behavior change in African young adults

Sexually transmitted infections (STIs) remain a significant public health concern among African young adults, driven by limited knowledge, high-risk behaviors, stigma, and inadequate access to care. While mobile health (mHealth) interventions offer potential, many existing tools lack cultural relevance, theoretical grounding, and adaptability. This study presents STI Shield, a multi-chatbot mobile application designed to enhance STI awareness and encourage safer sexual behaviors. The app integrates rule-based and large language model (LLM)-based chatbots to deliver structured education and personalized counseling, drawing on the Health Belief Model and Persuasive System Design principles. A two-phase evaluation involving African participants living both in Africa and outside Africa, comprising pilot and in-the-wild studies, demonstrated high usability and acceptability, strong educational impact, high persuasiveness, and positive shifts in key behavior change determinants. This work contributes to the fields of mHealth, conversational artificial intelligence, and human-computer interaction by offering a novel chatbot-based system model for delivering personalized, culturally relevant, and theory-driven digital health support in under-resourced settings.