Gary Hsieh
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Gary Hsieh has a total of 111 co-authors. Here are the top co-authors by number of shared publications:
- Donghoon Shin
University of Washington, Seattle, WA, USA
8 shared publications - Ruican Zhong
University of Washington, Seattle, Washington, USA
4 shared publications - Anthony Tang
Singapore Management University, Singapore, Singapore
3 shared publications - Kate Starbird
Human Centered Design & Engineering, University of Washington, Seattle, Washington, USA
3 shared publications - Lucy Lu Wang
Information School, University of Washington, Seattle, Washington, USA and Allen Institute for AI, Seattle, Washington, USA
3 shared publications - Ruoxi Shang
University of Washington, Seattle, Washington, USA
3 shared publications
Latest Publications
- Open Access
- 10 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 148-153
“I Wasn’t the Only One”: Podcasting as Sociotechnical Infrastructure for Religious Deconstruction, Transition, and Reconfiguration in High-Demand Communities
- 10 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 148-153
Open Access“I Wasn’t the Only One”: Podcasting as Sociotechnical Infrastructure for Religious Deconstruction, Transition, and Reconfiguration in High-Demand Communities
- Open Access
- 23 September 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 10 (6) , 1-27
"I Can’t Respond to Everyone": An Empirical Investigation of Social Media Influencers’ Management of Controversies
Social Media Influencers (SMIs) are vital assets to social media platforms, attracting substantial audiences and driving engagement. However, their heightened visibility also subjects them to intense public scrutiny, leaving them particularly vulnerable when engaging in controversial behavior or making contentious statements. In such moments, SMIs must decide how to respond in ways intended to de-escalate controversy. This study examines how SMIs make strategic decisions following controversial events, the challenges they encounter, and how audiences interpret and react to these responses, revealing critical misalignments between the two perspectives. Through interviews with eight SMIs and fourteen viewer members in a Mandarin-speaking East Asian context, we outline key considerations SMIs weigh during controversies, the significant challenges they encounter, the aspects where audiences commonly express dissatisfaction with SMI responses. Our findings pinpoint three critical areas of misalignment: the interpretation of delayed responses, the selection of target audiences, and the awareness of underlying reasons behind SMIs’ emotional self-protection strategies.
- 23 September 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 10 (6) , 1-27
Open Access"I Can’t Respond to Everyone": An Empirical Investigation of Social Media Influencers’ Management of Controversies
Social Media Influencers (SMIs) are vital assets to social media platforms, attracting substantial audiences and driving engagement. However, their heightened visibility also subjects them to intense public scrutiny, leaving them particularly vulnerable when engaging in controversial behavior or making contentious statements. In such moments, SMIs must decide how to respond in ways intended to de-escalate controversy. This study examines how SMIs make strategic decisions following controversial events, the challenges they encounter, and how audiences interpret and react to these responses, revealing critical misalignments between the two perspectives. Through interviews with eight SMIs and fourteen viewer members in a Mandarin-speaking East Asian context, we outline key considerations SMIs weigh during controversies, the significant challenges they encounter, the aspects where audiences commonly express dissatisfaction with SMI responses. Our findings pinpoint three critical areas of misalignment: the interpretation of delayed responses, the selection of target audiences, and the awareness of underlying reasons behind SMIs’ emotional self-protection strategies.
- Open Access
- 13 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 2765-2779
Group Conversational Agents: A Review of Designs that Support and Shape Group Interaction
- 13 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 2765-2779
Open AccessGroup Conversational Agents: A Review of Designs that Support and Shape Group Interaction
- Open Access
- 13 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 588-604
ReFinE: Streamlining UI Mockup Iteration with Research Findings
- 13 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 588-604
Open AccessReFinE: Streamlining UI Mockup Iteration with Research Findings
- Open Access
- 30 April 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 10 (2) , 1
Corrigendum: Rethinking Teaching Evaluation Reports: Designing AI-transformed Student Feedback for Instructor Engagement
This is a corrigendum for the article "Rethinking Teaching Evaluation Reports: Designing AI-transformed Student Feedback for Instructor Engagement" published in Proc. ACM Hum.-Comput. Interact. 9, 7, Article CSCW320 (November 2025), 40 pages.
- 30 April 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 10 (2) , 1
Open AccessCorrigendum: Rethinking Teaching Evaluation Reports: Designing AI-transformed Student Feedback for Instructor Engagement
This is a corrigendum for the article "Rethinking Teaching Evaluation Reports: Designing AI-transformed Student Feedback for Instructor Engagement" published in Proc. ACM Hum.-Comput. Interact. 9, 7, Article CSCW320 (November 2025), 40 pages.
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Behind The Paper: A Workflow for Supporting Personal Research Reflection
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Open AccessBehind The Paper: A Workflow for Supporting Personal Research Reflection
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-20
PaperTok: Exploring the Use of Generative AI for Creating Short-form Videos for Research Communication
The dissemination of scholarly research is critical, yet researchers often lack the time and skills to create engaging content for popular media such as short-form videos. To address this gap, we explore the use of generative AI to help researchers transform their academic papers into accessible video content. Informed by a formative study with science communicators and content creators (N = 8), we designed PaperTok, an end-to-end system that automates the initial creative labor by generating script options and corresponding audiovisual content from a source paper. Researchers can then refine based on their preferences with further prompting. A mixed-methods user study (N = 18) and crowdsourced evaluation (N = 100) demonstrate that PaperTok’s workflow can help researchers create engaging and informative short-form videos. We also identified the need for more fine-grained controls in the creation process. To this end, we offer implications for future generative tools that support science outreach.
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-20
Open AccessPaperTok: Exploring the Use of Generative AI for Creating Short-form Videos for Research Communication
The dissemination of scholarly research is critical, yet researchers often lack the time and skills to create engaging content for popular media such as short-form videos. To address this gap, we explore the use of generative AI to help researchers transform their academic papers into accessible video content. Informed by a formative study with science communicators and content creators (N = 8), we designed PaperTok, an end-to-end system that automates the initial creative labor by generating script options and corresponding audiovisual content from a source paper. Researchers can then refine based on their preferences with further prompting. A mixed-methods user study (N = 18) and crowdsourced evaluation (N = 100) demonstrate that PaperTok’s workflow can help researchers create engaging and informative short-form videos. We also identified the need for more fine-grained controls in the creation process. To this end, we offer implications for future generative tools that support science outreach.
- Open Access
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 222-230
Understanding the Effects of Conversational Agent Personality on the Credibility of LLM-Based Conversational Search
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 222-230
Open AccessUnderstanding the Effects of Conversational Agent Personality on the Credibility of LLM-Based Conversational Search
- Open Access
Synthetic Cognitive Walkthrough: Aligning Large Language Model Performance with Human Cognitive Walkthrough
Conducting usability testing like cognitive walkthrough (CW) can be costly. Recent developments in large language models (LLMs), with visual reasoning and UI navigation capabilities, present opportunities to automate CW. We explored whether LLMs (GPT-4 and Gemini-2.5-pro) can simulate human behavior in CW by comparing their walkthroughs with human participants. While LLMs could navigate interfaces and provide reasonable rationales, their behavior differed from humans. LLM-prompted CW achieved higher task completion rates than humans and followed more optimal navigation paths, while identifying fewer potential failure points. However, follow-up studies demonstrated that with additional prompting, LLMs can predict human-identified failure points, aligning their performance with human participants. Our work highlights that while LLMs may not replicate human behaviors exactly, they can be leveraged for scaling usability walkthroughs and providing UI insights, offering a valuable complement to traditional usability testing.
Open AccessSynthetic Cognitive Walkthrough: Aligning Large Language Model Performance with Human Cognitive Walkthrough
Conducting usability testing like cognitive walkthrough (CW) can be costly. Recent developments in large language models (LLMs), with visual reasoning and UI navigation capabilities, present opportunities to automate CW. We explored whether LLMs (GPT-4 and Gemini-2.5-pro) can simulate human behavior in CW by comparing their walkthroughs with human participants. While LLMs could navigate interfaces and provide reasonable rationales, their behavior differed from humans. LLM-prompted CW achieved higher task completion rates than humans and followed more optimal navigation paths, while identifying fewer potential failure points. However, follow-up studies demonstrated that with additional prompting, LLMs can predict human-identified failure points, aligning their performance with human participants. Our work highlights that while LLMs may not replicate human behaviors exactly, they can be leveraged for scaling usability walkthroughs and providing UI insights, offering a valuable complement to traditional usability testing.
- Open Access
- 16 October 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 9 (7) , 1-40
Rethinking Teaching Evaluation Reports: Designing AI-transformed Student Feedback for Instructor Engagement
Student feedback is critical for improving teaching, yet instructors often avoid reading evaluations due to emotional burden and information overload. We present a systematic exploration of how language models can distill and transform student evaluations into adaptive, actionable insights. Through a systematic design space exploration combining 4 feedback strategies (removing harmful content, paraphrasing criticism, sandwiching negatives, adding constructive suggestions) with 4 presentation formats (themes, cards, letters, chatbots), we created six AI-augmented prototypes of teaching evaluations. Interviews with 16 post-secondary instructors revealed that effective use of AI in feedback processing should: (1) support action formation through focused views and divergent thinking, (2) reduce emotional costs while enabling celebration and sharing, (3) facilitate longitudinal engagement and re-contextualization across terms, and (4) maintain transparency and preserve access to original context to build trust. Our work provides design guidelines for AI-augmented feedback systems and demonstrates how language models can adaptively process and present information based on feedback receivers' specific needs and contexts.
- 16 October 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 9 (7) , 1-40
Open AccessRethinking Teaching Evaluation Reports: Designing AI-transformed Student Feedback for Instructor Engagement
Student feedback is critical for improving teaching, yet instructors often avoid reading evaluations due to emotional burden and information overload. We present a systematic exploration of how language models can distill and transform student evaluations into adaptive, actionable insights. Through a systematic design space exploration combining 4 feedback strategies (removing harmful content, paraphrasing criticism, sandwiching negatives, adding constructive suggestions) with 4 presentation formats (themes, cards, letters, chatbots), we created six AI-augmented prototypes of teaching evaluations. Interviews with 16 post-secondary instructors revealed that effective use of AI in feedback processing should: (1) support action formation through focused views and divergent thinking, (2) reduce emotional costs while enabling celebration and sharing, (3) facilitate longitudinal engagement and re-contextualization across terms, and (4) maintain transparency and preserve access to original context to build trust. Our work provides design guidelines for AI-augmented feedback systems and demonstrates how language models can adaptively process and present information based on feedback receivers' specific needs and contexts.