Analyzing Polarization in Social Media: Method and Application to Tweets on 21 Mass Shootings

TL;DR

This paper introduces an NLP framework to analyze political polarization in social media, focusing on four linguistic dimensions, and applies it to a large dataset of tweets about mass shootings to reveal partisan differences.

Contribution

It presents a novel NLP-based approach for analyzing polarization through multiple linguistic dimensions and demonstrates its effectiveness on a large-scale social media dataset.

Findings

Polarization is mainly driven by framing differences, not topic choice.

Republicans focus more on shooter and facts, Democrats on victims and policy.

The proposed clustering method yields more cohesive topics than LDA.

Abstract

We provide an NLP framework to uncover four linguistic dimensions of political polarization in social media: topic choice, framing, affect and illocutionary force. We quantify these aspects with existing lexical methods, and propose clustering of tweet embeddings as a means to identify salient topics for analysis across events; human evaluations show that our approach generates more cohesive topics than traditional LDA-based models. We apply our methods to study 4.4M tweets on 21 mass shootings. We provide evidence that the discussion of these events is highly polarized politically and that this polarization is primarily driven by partisan differences in framing rather than topic choice. We identify framing devices, such as grounding and the contrasting use of the terms "terrorist" and "crazy", that contribute to polarization. Results pertaining to topic choice, affect and illocutionary force suggest that Republicans focus more on the shooter and event-specific facts (news) while Democrats focus more on the victims and call for policy changes. Our work contributes to a deeper understanding of the way group divisions manifest in language and to computational methods for studying them.