Problem
Research questions and friction points this paper is trying to address.
menstrual health
cultural stigma
health education
intimate health
trusted resources
Designing Around Stigma: Human-Centered LLMs for Menstrual Health
🤖 AI Summary
This study addresses the challenges Pakistani women face in accessing reliable menstrual health information due to cultural taboos and educational gaps. To tackle this, the authors propose a human-centered AI design framework tailored for stigmatized health topics and implement it in a WhatsApp-based chatbot that integrates a large language model with Retrieval-Augmented Generation (RAG). The system supports Roman Urdu, incorporates an expert-validated knowledge base, and was co-designed with female university students to ensure cultural appropriateness and gender-sensitive interaction. During a two-week deployment, 403 user messages and interview data revealed that participants used the chatbot to challenge taboos, validate previously dismissed health concerns, and actively construct reproductive health knowledge. These findings underscore the critical role of expert validation, culturally grounded interpretive models, and localized interaction design in deploying AI for sensitive health domains.
📝 Abstract
Menstrual health education (MHE) in Pakistan is constrained by cultural taboos and inadequate formal curricula, leaving women with few trusted resources to lean on. In response to these challenges, we introduce a WhatsApp-based chatbot powered by a large language model (LLM) and Retrieval Augmented Generation (RAG), co-designed with Pakistani college women. Workshops (N=30) revealed key design requirements -- support for Roman Urdu, use of subsidized platforms, and an expert -- curated knowledge base. We then deployed the chatbot with 13 participants for two weeks (403 messages and interviews). Women used it to challenge cultural taboos, legitimize health concerns often dismissed as normal, and build reproductive health knowledge through iterative questioning. Yet, interactions also exposed tensions: reliance on cultural explanatory models, questions of trust and validation, and gendered persona of the chatbot itself. We contribute empirical insights, a stigma-aware design framework for culturally sensitive conversational AI, and a methodological lens foregrounding expert validation in intimate health domains.
Innovation
Methods, ideas, or system contributions that make the work stand out.
stigma-aware design
retrieval-augmented generation
culturally sensitive AI
menstrual health education
expert-curated knowledge base
🔎 Similar Papers
No similar papers found.
