百晓学者学者目录
Hanying Wei

Hanying Wei

Ph.D. Candidate
Columbia University

hanying.wei@columbia.edu

Biography

Hanying Wei is a Ph.D. Candidate in the Department of Political Science at Columbia University, specializing in Quantitative Methodology and Computational Social Science. She also holds an M.A. in Statistics from Columbia University (expected), an M.Phil. in Social Science from Hong Kong University of Science and Technology, and an M.Eng. in Computer Technology from Peking University. Her research focuses on applying large language models and computational methods to social science problems, including design-based supervised learning for imperfect surrogates and analyzing political imagery for public opinion. Prior to her academic career, she worked as a Software Engineer at Veritas and held internships at Mobvoi and Microsoft. She has received multiple fellowships and awards, including the Yu San Wa Taiwan Fellowship, Dracopoulos Fellow, and the Gosnell Prize.

Selected Publications

Journal Articles

2027

Using Large Language Model Annotations for the Social Sciences: A General Framework of Using Predicted Variables in Downstream Analyses

Naoki Egami, Musashi Hinck, Brandon M. Stewart, Hanying Wei

American Journal of Political Science (Conditionally Accepted)

2023

Using Imperfect Surrogates for Downstream Inference: Design-based Supervised Learning for Social Science Applications of Large Language Models

Naoki Egami, Musashi Hinck, Brandon M. Stewart, Hanying Wei

Neural Information Processing Systems (NeurIPS)