Designing Around Stigma: Human-Centered LLMs for Menstrual Health

TL;DR

This paper presents a culturally sensitive, WhatsApp-based LLM chatbot co-designed with Pakistani women to improve menstrual health education amid cultural taboos, revealing both its potential and challenges.

Contribution

It introduces a stigma-aware design framework for conversational AI in sensitive health domains, with empirical insights from deployment in Pakistan.

Findings

Women used the chatbot to challenge taboos and legitimize health concerns.

Interactions revealed tensions around trust, validation, and gendered personas.

The study provides a methodological lens emphasizing expert validation.

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.