Follow the Echo Chamber: Ideological Sorting on Twitter

Abstract:

While numerous studies examine the relationship between social media and political behavior, scholars continue to debate its effects on political polarization. To inform this debate, we measure the effect of social media echo chambers on public opinion by evaluating 40,000 tweets around major breaking news stories, and comparing pre-and post-event policy positions amongst far and moderate right, and far and moderate left groups on Twitter. Our research improves on current approaches of measuring polarization by combining network analysis with supervised machine learning to examine what sampled individuals within different social media networks actually say about political topics. We find that individuals’ opinions on a variety of political issues converge on the modal opinion of media elites within their echo chamber following large-scale media events. We use this evidence to argue that people become more ideologically sorted—rather than more ideologically polarized—vis-à-vis social media echo chambers.  

Speaker Bio:

Image

Laura Jakli is a Predoctoral Fellow at the Center on Democracy, Development and the Rule of Law at Stanford University, and a Ph.D. Candidate in the Department of Political Science at the University of California, Berkeley. Her dissertation draws on digital survey and ad experiments, machine learning, and qualitative fieldwork to examine the relationship between digital politics and political radicalization. Her related research examines how digital networks shape migration patterns and refugee behavior. Her research appears in International Studies Quarterly and the Virginia Journal of International Law. Her co-authored book chapter is forthcoming in Democratization (Oxford University Press).