● 주제: Mind mining from responses to randomized paired comparisons

● 발표자: 강정한 교수(서울대학교 사회학과)

Jeong-han Kang received Ph.D. in sociology from University of Chicago, was Professor of Sociology at Yonsei University, and currently is Professor of Sociology at Seoul National University. His recent research interests include digital transformation, narrative-driven data science, and science of science with a gender perspective. His studies have been published in Journal of Informetrics, Social Policy & Administration, Proceedings of the Web Conference (WWW), Journal of Mathematical Sociology, Sociological Methods and Research, and Administrative Science Quarterly. 

● 시간 및 장소: 2026년 10월 2일(금) 12:00~13:00, 온라인 Zoom

https://snu-ac-kr.zoom.us/j/85214423474

회의 ID: 852 1442 3474

● Abstract: Randomized paired comparisons (RPC) for social values have various advantages over a matrix format of multiple items; however, their use cannot exhaust all possible pairs if there are too many items to compare one-to-one. This article proposes (1) applying a dimension reduction method, structural topic modeling (STM), to RPC survey data by restructuring answers into ordered pairs to estimate latent answering patterns, (2) visualizing them into directed graphs, and (3) interpreting them as respondents’ preference structures among social values. For empirical validation, we randomly divided 920 respondents into RPC and matrix-format groups and asked about the seriousness of ten social problems. Our STM from the RPC group revealed five preference structures beyond a linear order among the 10 items, which are interpretable and incorporate statistical tests with respondents’ traits as covariates. We also discuss how to improve topic modeling with RPC and contribute to various research streams.

● 주최: 서울대학교 SSK 〈포스트팬데믹 시기 디지털 소통과 지속 가능성〉 연구단, 서울대학교 언론정보연구소