🤖 AI Summary
This study addresses the limitations of traditional focus groups—namely their heavy reliance on skilled moderators and high operational costs—and the lack of methodological support in existing AI meeting tools. It proposes the first AI-support framework specifically designed for focus groups, structuring the design space along two dimensions: AI role (tool, co-moderator, moderator) and interaction modality (text, voice, embodied). The framework delineates interaction trade-offs and methodological risks associated with different combinations of these dimensions. By integrating generative AI capabilities such as real-time prompting, turn-taking regulation, thematic mapping, and instant summarization, and grounding them in human-computer interaction and user experience principles, the work develops a structured design guide. This reveals how AI intervention shapes group dialogue dynamics and articulates key research questions for evaluating the effectiveness of AI-augmented focus groups.
📝 Abstract
Collecting participants' lived experiences is central to design research. Focus groups are uniquely valuable because participants not only share individual accounts but also respond to one another, surfacing comparison, disagreement, and collective sensemaking. However, focus groups are resource-intensive and highly sensitive to facilitation: moderators must probe for specificity, balance participation, manage topic flow, and sustain psychological safety, and subtle facilitation choices can shape what becomes salient. Recent HCI work and commercial meeting tools show that generative AI can scaffold live conversation through prompting, turn regulation, thematic mapping, and real-time summarization. Yet UXR teams lack a clear map of what these capabilities mean in focus groups and what methodological risks they introduce. We synthesize AI supports for live conversation and translate them into a focus-group-specific playbook organized by AI role (tool, co-host, host) and modality (text, voice, embodied).We synthesize prior work on AI-supported live conversation and propose a focus-group-specific playbook of AI supports organized by role (tool, co-host, host) and modality (text, voice, embodied). We characterize interactional trade-offs and identify open questions for evaluating AI-supported focus groups as methodological configurations.