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


Recommended citation: Hans W. A. Hanley and Zakir Durumeric. "Twits, Toxic Tweets, and Tribal Tendencies: Trends in Politically Polarized Posts on Twitter." (2023).

Social media platforms are often blamed for exacerbating political polarization and worsening public dialogue. Many claim hyperpartisan users post pernicious content, slanted to their political views encouraging raucous and otherwise toxic conversations. However, what factors, actually contribute to increased online toxicity and negative interactions?

Within this work, we explore the role that political ideology plays in contributing to toxicity both on an individual user level and a topic level on Twitter. First, after collecting 187~million tweets from 55,415~Twitter users, we determine how several account-level characteristics including political ideology, user toxicity norms, and account age contribute to how often each user posts toxic content. Running a linear regression, we find, rather than each account’s political ideology, that the diversity of different views and the toxicity norms of the account with which that user engages has a more marked effect on their own toxicity. Namely, as users engage with a wider array of political views, we find that they post more toxic content. 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 6,955 different topics, with topics becoming more toxic as a wider diversity of users are involved.