THE UNIVERSITY OF CHICAGO
My research intersects computational social science, large language models (LLMs), social media, and social neuroscience. My recent work focuses on fine-tuning LLMs using social survey data, aiming to predict unmeasured public opinions. Additionally, I have applied quasi-experimental, causal inference methods to large-scale social media data to study how misinformation moderation could unintentionally reinforce echo chambers. My works have been published in Proceedings of the National Academy of Sciences (PNAS) and other venues.
Recent Research / Recent Publications
Junsol Kim, Zhao Wang, Haohan Shi, Hsin-Keng Ling, James Evans (2023). Individual misinformation tagging reinforces echo chambers; Collective tagging does not. arXiv preprint arXiv:2311.11282.
Junsol Kim, Byungkyu Lee (2023). AI-Augmented Surveys: Leveraging Large Language Models for Opinion Prediction in Nationally Representative Surveys. arXiv preprint arXiv:2305.09620.
Ryan Hyon, Yoosik Youm, Junsol Kim, Jeanyung Chey, Seyul Kwak, Carolyn Parkinson. (2020). Similarity in functional brain connectivity at rest predicts interpersonal closeness in the social network of an entire village. Proceedings of the National Academy of Sciences, 117(52), 33149-33160.
Yoosik Youm, Junsol Kim, Seyul Kwak, Jeanyung Chey. (2021). Neural and social correlates of attitudinal brokerage: Using the complete social networks of two entire villages. Proceedings of the Royal Society B, 288(1944), 20202866.