Problem
Research questions and friction points this paper is trying to address.
Foreign Domestic Workers
caregiving burden
emotional support
language barriers
social isolation
Foreign Domestic Workers' Perspectives on an LLM-Based Emotional Support tool for Caregiving Burden
🤖 AI Summary
This study addresses the significant emotional caregiving burden experienced by migrant domestic care workers, who often face language barriers, social isolation, and limited access to support—challenges exacerbated by the lack of research on the applicability of emotional support technologies for this marginalized group. Through semi-structured interviews and guided interactions, the research explores how migrant domestic care workers in Singapore engage with large language model–driven chatbots as everyday, non-clinical emotional support tools. Inductive thematic analysis reveals three core design values: psychological safety and emotional validation, accessibility through tolerance of fragmented or non-standard language, and multifunctionality as a source of comfort, guidance, and companionship. These findings offer an innovative design perspective for developing emotionally supportive technologies tailored to the needs of underserved populations.
📝 Abstract
Foreign Domestic Workers (FDWs) play a central role in home-based eldercare yet often experience substantial emotional caregiving burden shaped by linguistic barriers, social isolation, and limited access to support. While caregiving burden has been extensively studied among familial caregivers, little is known about how FDWs engage with emotional support technologies. We present an exploratory qualitative study of how FDWs in Singapore interact with a Large Language Model (LLM)-driven chatbot as an everyday, non-clinical form of emotional support. Through interviews and guided chatbot interactions, we conducted an inductive thematic analysis of participants' experiences. We identify three design-relevant themes: chatbots were experienced as psychologically safe and emotionally validating; they supported linguistic accessibility by accommodating imperfect and fragmented language; and they were appropriated as multifunctional resources for reassurance, guidance, and companionship. We discuss implications for designing LLM-driven emotional support tools that foreground psychological safety, accessibility, and flexible appropriation.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Large Language Model
emotional support
foreign domestic workers
linguistic accessibility
psychological safety
🔎 Similar Papers
No similar papers found.
