IdeoTrace: A Framework for Ideology Tracing with a Case Study on the 2016 U.S. Presidential Election

TL;DR

IdeoTrace is a framework that analyzes social media data to estimate user and news source ideologies and track how user polarization evolved during the 2016 U.S. presidential election.

Contribution

The paper introduces IdeoTrace, a novel framework for jointly estimating user and news source ideologies and tracing their evolution over time in social media contexts.

Findings

Both liberal and conservative users became more polarized over time.

The framework successfully captures ideological shifts during the election period.

Applied to 47,508 Twitter users, demonstrating its scalability and effectiveness.

Abstract

The 2016 United States presidential election has been characterized as a period of extreme divisiveness that was exacerbated on social media by the influence of fake news, trolls, and social bots. However, the extent to which the public became more polarized in response to these influences over the course of the election is not well understood. In this paper we propose IdeoTrace, a framework for (i) jointly estimating the ideology of social media users and news websites and (ii) tracing changes in user ideology over time. We apply this framework to the last two months of the election period for a group of 47508 Twitter users and demonstrate that both liberal and conservative users became more polarized over time.