Reading Between the Tweets: Deciphering Ideological Stances of Interconnected Mixed-Ideology Communities

TL;DR

This paper presents a novel method using message passing in language models to analyze complex ideological stances within interconnected online communities, demonstrated on Twitter discussions of the 2020 U.S. election.

Contribution

It introduces a new approach leveraging message passing in language model fine-tuning to better understand nuanced ideologies in interconnected communities.

Findings

Higher alignment with survey results than existing methods

Effective in capturing complex inter-community ideological interactions

Demonstrates potential for nuanced ideological analysis in social media

Abstract

Recent advances in NLP have improved our ability to understand the nuanced worldviews of online communities. Existing research focused on probing ideological stances treats liberals and conservatives as separate groups. However, this fails to account for the nuanced views of the organically formed online communities and the connections between them. In this paper, we study discussions of the 2020 U.S. election on Twitter to identify complex interacting communities. Capitalizing on this interconnectedness, we introduce a novel approach that harnesses message passing when finetuning language models (LMs) to probe the nuanced ideologies of these communities. By comparing the responses generated by LMs and real-world survey results, our method shows higher alignment than existing baselines, highlighting the potential of using LMs in revealing complex ideologies within and across interconnected mixed-ideology communities.