"Koyi Sawaal Nahi Hai": Reimagining Maternal Health Chatbots for Collective, Culturally Grounded Care

2025-10-31

AI Summary

Existing LLM-driven maternal health chatbots for low-resource settings overlook critical sociocultural realities—such as shared mobile devices, collective household decision-making, low literacy, and culturally normative silence—leading to poor adoption. Method: We conducted a real-world WhatsApp-based deployment in Lahore, Pakistan, and introduced the Relational Chatbot Design Grammar (RCDG), featuring four principles: “agency-based consent” (replacing individual informed consent), “silence-as-participation” (reframing interaction norms), “intermittent usage” (accommodating sporadic device access), and “systemic fragility by default” (guiding robust design). Evaluation combined ethnographic observation, focus groups, and longitudinal user tracking. Contribution/Results: Findings reveal that non-adoption stems from relational social structures—not individual preferences. RCDG significantly enhanced feasibility of family-coordinated health management. This work provides a transferable methodological framework and empirical validation for culturally grounded, collectivity-aware AI design in global health contexts.

Technology Category

• Humans and AI: User Experience and Usability
• Application Domains: Humanities & Computational Social Science
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

In recent years, LLM-based maternal health chatbots have been widely deployed in low-resource settings, but they often ignore real-world contexts where women may not own phones, have limited literacy, and share decision-making within families. Through the deployment of a WhatsApp-based maternal health chatbot with 48 pregnant women in Lahore, Pakistan, we examine barriers to use in populations where phones are shared, decision-making is collective, and literacy varies. We complement this with focus group discussions with obstetric clinicians. Our findings reveal how adoption is shaped by proxy consent and family mediation, intermittent phone access, silence around asking questions, infrastructural breakdowns, and contested authority. We frame barriers to non-use as culturally conditioned rather than individual choices, and introduce the Relational Chatbot Design Grammar (RCDG): four commitments that enable mediated decision-making, recognize silence as engagement, support episodic use, and treat fragility as baseline to reorient maternal health chatbots toward culturally grounded, collective care.

Problem

• Addressing maternal health chatbot barriers in shared phone environments
• Overcoming cultural constraints on women's health decision-making processes
• Redesigning chatbots for collective care in low-resource settings

Innovation

• Relational Chatbot Design Grammar for mediated decisions
• Recognizing silence as engagement in maternal care
• Treating infrastructural fragility as baseline condition