Sympathy over Polarization: A Computational Discourse Analysis of Social Media Posts about the July 2024 Trump Assassination Attempt

2025-01-17

AI Summary

This study examines the short-term impact of the July 2024 attempted assassination of Donald Trump on public discourse on X (formerly Twitter). Employing large language model–based sentiment analysis, difference-in-differences (DID) causal inference, and BERTopic-based dynamic topic modeling, we compare cross-partisan and cross-regional sentiment and thematic shifts in the week before and after the event. Results indicate that the incident did not exacerbate political polarization; instead, it triggered a significant and robust cross-ideological sympathy effect. Public attention rapidly shifted from partisan conflict toward consensus-oriented themes—including security governance and democratic resilience. This is the first study to causally demonstrate—within a rigorous counterfactual framework—that major political violence may attenuate, rather than intensify, societal division. By moving beyond descriptive analysis, our work advances political communication research and crisis response scholarship through both empirical evidence and a novel methodological paradigm integrating causal inference with large-scale, semantically rich social media analytics.

Technology Category

• Application Domains: Humanities & Computational Social Science
• Reasoning under Uncertainty: Causality
• Natural Language Processing: Safety and Robustness

Application Category

• Social Networks and Social Media: Media and governance, opinion dynamics, filter bubbles, polarization
• Web Mining and Content Analysis: Sentiment analysis and opinion mining
• Security and Privacy: Large-scale security measurements

Abstract

On July 13, 2024, at the Trump rally in Pennsylvania, someone attempted to assassinate Republican Presidential Candidate Donald Trump. This attempt sparked a large-scale discussion on social media. We collected posts from X (formerly known as Twitter) one week before and after the assassination attempt and aimed to model the short-term effects of such a ``shock'' on public opinions and discussion topics. Specifically, our study addresses three key questions: first, we investigate how public sentiment toward Donald Trump shifts over time and across regions (RQ1) and examine whether the assassination attempt itself significantly affects public attitudes, independent of the existing political alignments (RQ2). Finally, we explore the major themes in online conversations before and after the crisis, illustrating how discussion topics evolved in response to this politically charged event (RQ3). By integrating large language model-based sentiment analysis, difference-in-differences modeling, and topic modeling techniques, we find that following the attempt the public response was broadly sympathetic to Trump rather than polarizing, despite baseline ideological and regional disparities.

Problem

• Public Sentiment
• Emotional Change
• Social Media Analysis

Innovation

• Advanced Data Analysis
• Social Media Sentiment
• Political Event Impact