Twits, Toxic Tweets, and Tribal Tendencies: Trends in Politically Polarized Posts on Twitter

TL;DR

This study investigates how partisanship and polarization influence toxicity on Twitter, revealing that engagement with diverse political views and topics correlates with increased toxic behavior, supported by a new, high-performing toxicity detection model.

Contribution

The paper introduces an open-source DeBERTa-based toxicity detector and analyzes large-scale Twitter data to identify factors linked to online toxicity and polarization effects.

Findings

Toxicity correlates with engagement across diverse political views.

Users interacting with a wider range of topics tend to post more toxic content.

Toxic content is consistent across various politically charged topics.

Abstract

Social media platforms are often blamed for exacerbating political polarization and worsening public dialogue. Many claim that hyperpartisan users post pernicious content, slanted to their political views, inciting contentious and toxic conversations. However, what factors are actually associated with increased online toxicity and negative interactions? In this work, we explore the role that partisanship and affective polarization play in contributing to toxicity both on an individual user level and a topic level on Twitter/X. To do this, we train and open-source a DeBERTa-based toxicity detector with a contrastive objective that outperforms the Google Jigsaw Perspective Toxicity detector on the Civil Comments test dataset. Then, after collecting 89.6 million tweets from 43,151 Twitter/X users, we determine how several account-level characteristics, including partisanship along the US left-right political spectrum and account age, predict how often users post toxic content. Fitting a Generalized Additive Model to our data, we find that the diversity of views and the toxicity of the other accounts with which that user engages has a more marked effect on their own toxicity. Namely, toxic comments are correlated with users who engage with a wider array of political views. Performing topic analysis on the toxic content posted by these accounts using the large language model MPNet and a version of the DP-Means clustering algorithm, we find similar behavior across 5,288 individual topics, with users becoming more toxic as they engage with a wider diversity of politically charged topics.