Granular Analysis of Social Media Users’ Truthfulness Stances Toward Climate Change Factual Claims

Haiqi Zhang, Zhengyuan Zhu, Zeyu Zhang, Jacob Devasier, Chengkai Li

Keywords: Taxonomy Construction, Truthfulness Stance Detection, Climate Change, LLM

Abstract: Climate change poses an urgent global problem that requires efficient data analysis mechanisms to provide insights into climate-related discussions on social media platforms. This paper presents a framework aimed at understanding social media users' perceptions of various climate change topics and uncovering the insights behind these perceptions. Our framework employs large language model to develop a taxonomy of factual claims related to climate change and build a classification model that detects the truthfulness stance of tweets toward the factual claims. The findings reveal two key conclusions: (1) The public tends to believe the claims are true, regardless of the actual claim veracity; (2) The public shows a lack of discernment between facts and misinformation across different topics, particularly in areas related to politics, economy, and environment.

Archival Submission: arxival

Submission Number: 31