Modeling Political Discourse with Sentence-BERT and BERTopic
This work addresses the challenge of understanding moral-driven topic evolution in political discourse on social media for researchers in social network analysis and computational political science, though it is incremental as it builds on existing methods like BERTopic and Moral Foundations Theory.
The study tackled the problem of analyzing political discourse on social media by developing a framework that integrates BERTopic-based topic modeling with Moral Foundations Theory to track topic evolution and moral dimensions in Twitter data from the 117th U.S. Congress, revealing that granular topics dissolve rapidly and moral foundations like Care and Loyalty dominate durable topics.
Social media has reshaped political discourse, offering politicians a platform for direct engagement while reinforcing polarization and ideological divides. This study introduces a novel topic evolution framework that integrates BERTopic-based topic modeling with Moral Foundations Theory (MFT) to analyze the longevity and moral dimensions of political topics in Twitter activity during the 117th U.S. Congress. We propose a methodology for tracking dynamic topic shifts over time and measuring their association with moral values and quantifying topic persistence. Our findings reveal that while overarching themes remain stable, granular topics tend to dissolve rapidly, limiting their long-term influence. Moreover, moral foundations play a critical role in topic longevity, with Care and Loyalty dominating durable topics, while partisan differences manifest in distinct moral framing strategies. This work contributes to the field of social network analysis and computational political discourse by offering a scalable, interpretable approach to understanding moral-driven topic evolution on social media.