Junsol Kim

Junsol Kim

PhD student in Sociology

University of Chicago

I am a third-year Ph.D. student in Sociology at the University of Chicago, advised by Professors James Evans and Byungkyu Lee. My research intersects computational social science, large language models (LLMs), social media, and causal inference. 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. You can find my CV here.

Interests
  • Political Sociology
  • Computational Social Science
  • Large Language Model
  • Social Media
  • Causal Inference
Education
  • PhD student in Sociology

    University of Chicago

  • MA in Sociology

    University of Chicago

  • BS/BA in Computer Science & Sociology

    Yonsei University

Selected Publications

(2023). Individual misinformation tagging reinforces echo chambers; Collective tagging does not.

PDF

(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.

PDF Code Dataset

(2021). A measure of centrality in cyclic diffusion processes: Walk-betweenness. PLoS ONE, 16(1), e0245476.

PDF Code Dataset

(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.

PDF Code Dataset

Demo

AI-Augmented Surveys
This demo site presents public opinion trends as predicted by General Social Survey (GSS)-based AI language models.