The reviewed record of science sign in
Pith

arxiv: 2606.11835 · v1 · pith:6BFTQUMS · submitted 2026-06-10 · cs.HC · cs.AI

Designing AI-Supported Focus Groups: A Role x Modality Playbook

Zhiqing Wang , Steven Dow This is my paper

Reviewed by Pith2026-06-27 08:35 UTCgrok-4.3pith:6BFTQUMSopen to challenge →

classification cs.HC cs.AI
keywords focus groupsAI facilitationgenerative AIUX research methodshuman-AI interactionlive conversationmethodological configurations
0
0 comments X

The pith

A role-by-modality playbook classifies AI supports for focus groups as tool, co-host or host across text, voice or embodied forms.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

Focus groups produce value through participants responding to one another and engaging in collective sensemaking, yet they demand precise facilitation that is costly and variable. Generative AI already handles tasks such as turn regulation, thematic mapping and real-time summarization in other live-conversation settings. The paper translates those capabilities into focus-group terms by building a two-axis playbook: AI can act as a passive tool, an active co-host or a full host, and it can operate through text, voice or embodied channels. Each combination produces distinct effects on topic control, participation balance and psychological safety. The result is a map that lets researchers choose configurations while surfacing the interactional trade-offs and evaluation questions that remain open.

Core claim

The paper establishes a focus-group-specific playbook of AI supports organized by role (tool, co-host, host) and modality (text, voice, embodied). It characterizes interactional trade-offs and identifies open questions for evaluating AI-supported focus groups as methodological configurations.

What carries the argument

The role-by-modality playbook that classifies AI capabilities for live focus-group conversations and surfaces their effects on participant interaction.

If this is right

  • Assigning AI the host role shifts control of topic flow and participation balance away from the human moderator.
  • Embodied modalities change the dynamics of psychological safety compared with text or voice channels.
  • Treating AI only as a tool keeps human facilitation central but limits the scale of real-time support.
  • The playbook makes explicit which methodological risks must be measured when any role-modality pair is deployed.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same matrix could be tested on related methods such as design workshops or stakeholder sessions.
  • New metrics focused on collective sensemaking quality would be needed to evaluate the configurations the playbook describes.
  • Commercial meeting platforms could expose the role and modality choices as selectable options for moderators.

Load-bearing premise

Capabilities shown in general live-conversation tools can be translated into focus-group contexts while preserving the core value of participant-to-participant interaction and psychological safety.

What would settle it

A controlled comparison of focus groups using AI as host versus human moderation that finds measurably lower depth of disagreement and collective sensemaking in the AI condition.

read the original 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.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

0 major / 2 minor

Summary. The paper synthesizes prior HCI and commercial work on AI-supported live conversation and proposes a focus-group-specific playbook of AI supports organized by AI role (tool, co-host, host) and modality (text, voice, embodied). It characterizes interactional trade-offs and identifies open questions for evaluating AI-supported focus groups as methodological configurations, without presenting new empirical data or validation studies.

Significance. If the playbook serves as a useful organizing device, the work could help UXR teams map existing AI conversation capabilities onto focus-group practice while directing attention to risks around participant interaction and psychological safety. The explicit framing of open questions rather than unsubstantiated claims of successful translation is a strength of the conceptual contribution. The stress-test concern regarding translation from general tools does not land as a load-bearing issue because the manuscript surfaces those exact conditions as matters for future empirical checking.

minor comments (2)
  1. [Abstract] Abstract: the contribution statement contains a duplicated sentence ("We synthesize AI supports for live conversation and translate them..." followed immediately by an almost identical sentence beginning "We synthesize prior work...").
  2. The playbook description would benefit from at least one concrete example per role-modality cell drawn from the cited literature to make the mapping more actionable for readers.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for the positive assessment of the manuscript as a synthesis and playbook that surfaces interactional trade-offs and open evaluation questions without unsubstantiated empirical claims. The recommendation for minor revision is noted; however, the report contains no specific major comments to address.

Circularity Check

0 steps flagged

No significant circularity in conceptual synthesis and framework proposal

full rationale

The paper performs a literature synthesis of existing AI conversation tools and proposes an organizing playbook by role and modality, while explicitly surfacing open questions around trade-offs, evaluation, and risks to psychological safety. No equations, fitted parameters, predictions, or derivations are present; the central contribution is an organizing device whose validity does not depend on reducing to self-citations or inputs by construction. The work is self-contained as a framework proposal.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The paper rests on the domain assumption that AI conversation supports from other contexts transfer meaningfully to focus groups; no free parameters or invented entities are introduced.

axioms (1)
  • domain assumption AI capabilities shown in general live conversation and meeting tools can be mapped to focus group facilitation contexts
    The abstract invokes this translation to justify creating the playbook while noting risks.

pith-pipeline@v0.9.1-grok · 5731 in / 1296 out tokens · 20761 ms · 2026-06-27T08:35:52.959263+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

40 extracted references · 1 canonical work pages

  1. [1]

    Mohammed Alsobay, David M Rothschild, Jake M Hofman, and Daniel G Goldstein. 2025. Bringing everyone to the table: An experimental study of llm-facilitated group decision making

    2025

  2. [2]

    Deepali Aneja, Rens Hoegen, Daniel McDuff, and Mary Czerwinski. 2021. Understanding conversational and expressive style in a multimodal embodied conversational agent. InProceedings of the 2021 CHI conference on human factors in computing systems. 1–10

    2021

  3. [3]

    Sumit Asthana, Sagi Hilleli, Pengcheng He, and Aaron Halfaker. 2025. Summaries, Highlights, and Action items: Design, implementation and evaluation of an LLM-powered meeting recap system.Proceedings of the ACM on Human-Computer Interaction9, 2 (2025), 1–29

    2025

  4. [4]

    Rosaline S Barbour. 2018. Doing focus groups. (2018)

    2018

  5. [5]

    Julia Cambre, Jessica Colnago, Jim Maddock, Janice Tsai, and Jofish Kaye. 2020. Choice of voices: A large-scale evaluation of text-to-speech voice quality for long-form content. InProceedings of the 2020 CHI Conference on Human Factors in Computing Systems. 1–13

    2020

  6. [6]

    Hancheng Cao, Chia-Jung Lee, Shamsi Iqbal, Mary Czerwinski, Priscilla NY Wong, Sean Rintel, Brent Hecht, Jaime Teevan, and Longqi Yang. 2021. Large scale analysis of multitasking behavior during remote meetings. InProceedings of the 2021 CHI conference on human factors in computing systems. 1–13

    2021

  7. [7]

    Xinyue Chen, Nathan Yap, Xinyi Lu, Aylin Gunal, and Xu Wang. 2025. MeetMap: Real-Time Collaborative Dialogue Mapping with LLMs in Online Meetings.Proceedings of the ACM on Human-Computer Interaction9, 2 (2025), 1–35

    2025

  8. [8]

    Lingwei Cheng and Alexandra Chouldechova. 2023. Overcoming algorithm aversion: A comparison between process and outcome control. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems. 1–27

    2023

  9. [9]

    Elijah L Claggett, Robert E Kraut, and Hirokazu Shirado. 2025. Relational ai: Facilitating intergroup cooperation with socially aware conversational support. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems. 1–22

    2025

  10. [10]

    James R Detert, Ethan R Burris, et al. 2016. Can your employees really speak freely.Harvard Business Review94, 1 (2016), 80–87

    2016

  11. [11]

    Barbara DiCicco-Bloom and Benjamin F Crabtree. 2006. The qualitative research interview.Medical education40, 4 (2006), 314–321

    2006

  12. [12]

    Hyo Jin Do, Ha-Kyung Kong, Pooja Tetali, Karrie Karahalios, and Brian P Bailey. 2023. Inform, explain, or control: Techniques to adjust end-user performance expectations for a conversational agent facilitating group chat discussions.Proceedings of the ACM on Human-Computer Interaction7, CSCW2 (2023), 1–26

    2023

  13. [13]

    Nicolas Fay, Simon Garrod, and Jean Carletta. 2000. Group discussion as interactive dialogue or as serial monologue: The influence of group size. Psychological science11, 6 (2000), 481–486

    2000

  14. [14]

    Jessica He, Stephanie Houde, Gabriel E Gonzalez, Darío Andrés Silva Moran, Steven I Ross, Michael Muller, and Justin D Weisz. 2024. AI and the Future of Collaborative Work: Group Ideation with an LLM in a Virtual Canvas. InProceedings of the 3rd Annual Meeting of the Symposium on Human-Computer Interaction for Work. 1–14

    2024

  15. [15]

    Mo Houtti, Moyan Zhou, Loren Terveen, and Stevie Chancellor. 2025. Observe, ask, intervene: Designing AI agents for more inclusive meetings. In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems. 1–18

    2025

  16. [16]

    Margaret Hughes, Brandon C Roy, and Deb Roy. 2024. In Pursuit of Constructive Communication: Designing Tools to Support Development of Constructive Communication Metrics. InCompanion Publication of the 2024 ACM Designing Interactive Systems Conference. 121–124

    2024

  17. [17]

    Bietz, Nitesh Goyal, Nicole Immorlica, Blair MacIntyre, Andrés Monroy-Hernández, Benjamin C

    Matthew J. Bietz, Nitesh Goyal, Nicole Immorlica, Blair MacIntyre, Andrés Monroy-Hernández, Benjamin C. Pierce, Sean Rintel, and Donghee Yvette Wohn. 2022. Social presence in virtual event spaces. InCHI Conference on Human Factors in Computing Systems Extended Abstracts. 1–5

    2022

  18. [18]

    Soomin Kim, Jinsu Eun, Changhoon Oh, Bongwon Suh, and Joonhwan Lee. 2020. Bot in the bunch: Facilitating group chat discussion by improving efficiency and participation with a chatbot. InProceedings of the 2020 CHI Conference on Human Factors in Computing Systems. 1–13

    2020

  19. [19]

    2014.Focus groups: A practical guide for applied research

    Richard A Krueger. 2014.Focus groups: A practical guide for applied research. Sage publications

    2014

  20. [20]

    Zhe Liu. 2025. Interview AI-ssistant: Designing for Real-Time Human-AI Collaboration in Interview Preparation and Execution. InCompanion Proceedings of the 30th International Conference on Intelligent User Interfaces. 225–228

    2025

  21. [21]

    Heng Luo, Ying Chen, Tianjiao Chen, Tiffany A Koszalka, and Qinna Feng. 2023. Impact of role assignment and group size on asynchronous online discussion: An experimental study.Computers & Education192 (2023), 104658

    2023

  22. [22]

    Shuai Ma, Ying Lei, Xinru Wang, Chengbo Zheng, Chuhan Shi, Ming Yin, and Xiaojuan Ma. 2023. Who should i trust: Ai or myself? leveraging human and ai correctness likelihood to promote appropriate trust in ai-assisted decision-making. InProceedings of the 2023 CHI Conference on Human Factors in Computing Systems. 1–19

    2023

  23. [23]

    2018.Basic and advanced focus groups

    David L Morgan. 2018.Basic and advanced focus groups. Sage Publications

    2018

  24. [24]

    Prasanth Murali, Javier Hernandez, Daniel McDuff, Kael Rowan, Jina Suh, and Mary Czerwinski. 2021. Affectivespotlight: Facilitating the communication of affective responses from audience members during online presentations. InProceedings of the 2021 CHI Conference on Human Factors in Computing Systems. 1–13

    2021

  25. [25]

    Thomas Neumayr, Banu Saatci, Sean Rintel, Clemens Nylandsted Klokmose, and Mirjam Augstein. 2021. What was hybrid? a systematic review of hybrid collaboration and meetings research.arXiv preprint arXiv:2111.06172(2021)

    work page arXiv 2021

  26. [26]

    Alexander Newman, Ross Donohue, and Nathan Eva. 2017. Psychological safety: A systematic review of the literature.Human resource management review27, 3 (2017), 521–535

    2017

  27. [27]

    Catherine S Oh, Jeremy N Bailenson, and Gregory F Welch. 2018. A systematic review of social presence: Definition, antecedents, and implications. Frontiers in Robotics and AI5 (2018), 114. Manuscript submitted to ACM Designing AI-Supported Focus Groups: A Role×Modality Playbook 9

    2018

  28. [28]

    Anthony J Onwuegbuzie, Wendy B Dickinson, Nancy L Leech, and Annmarie G Zoran. 2009. A qualitative framework for collecting and analyzing data in focus group research.International journal of qualitative methods8, 3 (2009), 1–21

    2009

  29. [29]

    Payod Panda, Molly Jane Nicholas, Mar Gonzalez-Franco, Kori Inkpen, Eyal Ofek, Ross Cutler, Ken Hinckley, and Jaron Lanier. 2022. Alltogether: Effect of avatars in mixed-modality conferencing environments. InProceedings of the 1st annual meeting of the symposium on human-computer interaction for work. 1–10

    2022

  30. [30]

    Gun Woo Park, Payod Panda, Lev Tankelevitch, and Sean Rintel. 2024. The coexplorer technology probe: A generative ai-powered adaptive interface to support intentionality in planning and running video meetings. InProceedings of the 2024 ACM Designing Interactive Systems Conference. 1638–1657

    2024

  31. [31]

    Jude Abishek Rayan, Shaokang Jiang, Nishant Balaji, Jinmao Wang, Ian Gross, Cole Biehle, and Steven P Dow. 2025. Cueing the Crowd: LLM-Driven Conversational Cues Across Different Meeting Modalities Increase Topical Diversity of Generated Ideas. InProceedings of the ACM Collective Intelligence Conference. 297–316

    2025

  32. [32]

    2011.Qualitative interviewing: The art of hearing data

    Herbert J Rubin and Irene S Rubin. 2011.Qualitative interviewing: The art of hearing data. sage

    2011

  33. [33]

    Samiha Samrose, Daniel McDuff, Robert Sim, Jina Suh, Kael Rowan, Javier Hernandez, Sean Rintel, Kevin Moynihan, and Mary Czerwinski. 2021. Meetingcoach: An intelligent dashboard for supporting effective & inclusive meetings. InProceedings of the 2021 CHI conference on human factors in computing systems. 1–13

    2021

  34. [34]

    2008.Doing qualitative research: A comprehensive guide

    David Silverman and Amir Marvasti. 2008.Doing qualitative research: A comprehensive guide. Sage

    2008

  35. [35]

    Venkatesh Sivaraman, Leigh A Bukowski, Joel Levin, Jeremy M Kahn, and Adam Perer. 2023. Ignore, trust, or negotiate: understanding clinician acceptance of AI-based treatment recommendations in health care. InProceedings of the 2023 CHI Conference on Human Factors in Computing Systems. 1–18

    2023

  36. [36]

    Xinru Wang and Ming Yin. 2023. Watch out for updates: Understanding the effects of model explanation updates in ai-assisted decision making. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems. 1–19

    2023

  37. [37]

    Magdalena Wischnewski, Nicole Krämer, and Emmanuel Müller. 2023. Measuring and understanding trust calibrations for automated systems: A survey of the state-of-the-art and future directions. InProceedings of the 2023 CHI conference on human factors in computing systems. 1–16

    2023

  38. [38]

    Alexander Wuttke, Matthias Aßenmacher, Christopher Klamm, Max Lang, and Fraue Kreuter. 2025. AI conversational interviewing: Transforming surveys with LLMs as adaptive interviewers. 179–204 pages

    2025

  39. [39]

    Haijun Xia, Tony Wang, Aditya Gunturu, Peiling Jiang, William Duan, and Xiaoshuo Yao. 2023. CrossTalk: Intelligent substrates for language-oriented interaction in video-based communication and collaboration. InProceedings of the 36th Annual ACM Symposium on User Interface Software and Technology. 1–16

    2023

  40. [40]

    Tingting Yang, Heng Luo, and Di Sun. 2022. Investigating the combined effects of group size and group composition in online discussion.Active learning in higher education23, 2 (2022), 115–128. Manuscript submitted to ACM

    2022