Designing Around Stigma: Human-Centered LLMs for Menstrual Health
This work addresses menstrual health education for women in Pakistan, offering a culturally sensitive AI solution, though it is incremental as it builds on existing chatbot and RAG methods for a specific domain.
The researchers tackled the problem of menstrual health education in Pakistan, where cultural taboos limit access to trusted resources, by developing a WhatsApp-based chatbot using LLM and RAG, co-designed with 30 college women and deployed with 13 participants over two weeks, resulting in 403 messages and interviews that helped women challenge taboos and build health knowledge.
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.