I Am Not Them: Fluid Identities and Persistent Out-group Bias in Large Language Models

no code implementations • 16 Feb 2024 • Wenchao Dong, Assem Zhunis, Hyojin Chin, Jiyoung Han, Meeyoung Cha

The results indicate that when imbued with a particular social identity, ChatGPT discerns in-group and out-group, embracing in-group values while eschewing out-group values.

Prompt Engineering

Disentangling Structure and Style: Political Bias Detection in News by Inducing Document Hierarchy

no code implementations • 5 Apr 2023 • Jiwoo Hong, Yejin Cho, Jaemin Jung, Jiyoung Han, James Thorne

Our approach overcomes this limitation by considering both the sentence-level semantics and the document-level rhetorical structure, resulting in a more robust and style-agnostic approach to detecting political bias in news articles.

Bias Detection Document Classification +1

Detecting Contextomized Quotes in News Headlines by Contrastive Learning

no code implementations • 9 Feb 2023 • Seonyeong Song, Hyeonho Song, Kunwoo Park, Jiyoung Han, Meeyoung Cha

Quotes are critical for establishing credibility in news articles.

Contrastive Learning

Risk Communication in Asian Countries: COVID-19 Discourse on Twitter

1 code implementation • 22 Jun 2020 • Sungkyu Park, Sungwon Han, Jeongwook Kim, Mir Majid Molaie, Hoang Dieu Vu, Karandeep Singh, Jiyoung Han, Wonjae Lee, Meeyoung Cha

This finding calls for a need to analyze the public discourse by new measures, such as topical dynamics.

Social and Information Networks

The Fallacy of Echo Chambers: Analyzing the Political Slants of User-Generated News Comments in Korean Media

no code implementations • WS 2019 • Jiyoung Han, Youngin Lee, Junbum Lee, Meeyoung Cha

This study analyzes the political slants of user comments on Korean partisan media.