IdeoTrace: A Framework for Ideology Tracing with a Case Study on the 2016 U.S. Presidential Election
This addresses the need to understand how social media influences public polarization, particularly during divisive events like elections, though it is incremental as it applies existing methods to a specific case.
The paper tackles the problem of measuring political polarization on social media during the 2016 U.S. presidential election by proposing IdeoTrace, a framework for jointly estimating ideology of users and news sites and tracing changes over time; it finds that both liberal and conservative users became more polarized, with results based on 47,508 Twitter users over two months.
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.