Joon Sung Park

Joon Sung Park

Auto-generated profile, based on publicly available information

Joon Sung Park

Stanford University, Palo Alto, CA, USA

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 October 2023
Verified
Conference Paper
Open access
JPJoon Sung Park
Joon Sung Park
JOJoseph O'BRien
Joseph O'BRien
CCCarrie Jun Cai
Carrie Jun Cai
MMMeredith Ringel Morris
Meredith Ringel Morris
PLPercy Liang
Percy Liang
MBMichael S. Bernstein
Michael S. Bernstein

14 April 2023 in Proceedings of the ACM on Human-Computer Interaction
Verified
Journal Article
Open access
EKElise Karinshak
Elise Karinshak
SLSunny Xun Liu
Sunny Xun Liu
JPJoon Sung Park
Joon Sung Park
JHJeffrey T. Hancock
Jeffrey T. Hancock
Artificial Intelligence (AI) is a transformative force in communication and messaging strategy, with potential to disrupt traditional approaches. Large language models (LLMs), a form of AI, are capable of generating high-quality, humanlike text. We investigate the persuasive quality of AI-generated messages to understand how AI could impact public health messaging. Specifically, through a series of studies designed to characterize and evaluate generative AI in developing public health messages, we analyze COVID-19 pro-vaccination messages generated by GPT-3, a state-of-the-art instantiation of a large language model. Study 1 is a systematic evaluation of GPT-3's ability to generate pro-vaccination messages. Study 2 then observed peoples' perceptions of curated GPT-3-generated messages compared to human-authored messages released by the CDC (Centers for Disease Control and Prevention), finding that GPT-3 messages were perceived as more effective, stronger arguments, and evoked more positive attitudes than CDC messages. Finally, Study 3 assessed the role of source labels on perceived quality, finding that while participants preferred AI-generated messages, they expressed dispreference for messages that were labeled as AI-generated. The results suggest that, with human supervision, AI can be used to create effective public health messages, but that individuals prefer their public health messages to come from human institutions rather than AI sources. We propose best practices for assessing generative outputs of large language models in future social science research and ways health professionals can use AI systems to augment public health messaging.

27 September 2025
Verified
Conference Paper
Open access
OSOmar Shaikh
Omar Shaikh
SSShardul Sapkota
Shardul Sapkota
SRShan Rizvi
Shan Rizvi
EHEric Horvitz
Eric Horvitz
JPJoon Sung Park
Joon Sung Park
MBMichael S. Bernstein
Michael S. Bernstein

14 October 2023
Verified
Conference Paper
Open access
HSHong Shen
Hong Shen
TLTianshi Li
Tianshi Li
TLToby Jia-Jun Li
Toby Jia-Jun Li
JPJoon Sung Park
Joon Sung Park
DYDiyi Yang
Diyi Yang
The emergence of Large Language Models (LLMs) has brought both excitement and concerns to social computing research. On the one hand, LLMs offer unprecedented capabilities in analyzing vast amounts of textual data and generating human-like responses, enabling researchers to delve into complex social phenomena. On the other hand, concerns are emerging regarding the validity, privacy, and ethics of the research when LLMs are involved. This SIG aims at offering an open space for social computing researchers who are interested in understanding the impacts of LLMs to discuss their current practices, perspectives, challenges when engaging with LLMs in their everyday work and collectively shaping the emerging norms of using LLMs in social computing research.

29 October 2023
Verified
Conference Paper
Open access
MBMichael S. Bernstein
Michael S. Bernstein
JPJoon Sung Park
Joon Sung Park
MMMeredith Ringel Morris
Meredith Ringel Morris
SASaleema Amershi
Saleema Amershi
LCLydia B Chilton
Lydia B Chilton
MGMitchell L. Gordon
Mitchell L. Gordon
The new generation of generative AI models offers interactive opportunities that may fulfill long-standing aspirations in human-computer interaction and open doors to new forms of interaction that we have yet to imagine. The UIST community has a unique vantage point that can lead to critical contributions in envisioning a future of interactive computing that appropriately leverages the power of these new generative AI models. However, we are only just beginning to understand the research area that exists at the intersection of interaction and generative AI. By bringing together members of the UIST community interested in this intersection, we seek to initiate discussions on the potential of generative AI in architecting new forms of interactions. Key topics of interest include the exploration of novel categories of interactions made possible by generative AI, the development of methods for enabling more powerful and direct user control of generative AI, and the identification of model and architecture requirements for generative AI in interaction literature. The workshop will foster community building and produce concrete deliverables, including a research agenda, model/architecture requirements, and a simulated debate generated by a generative agent architecture.