Modeling Ideology and Predicting Policy Change with Social Media

Abstract

Social media has emerged as a prominent platform where people can express their feelings about social and political issues of our time. We study the many voices discussing an issue within a constituency and how they reflect ideology and may signal the outcome of important policy decisions. Focusing on the issue of same-sex marriage legalization, we examine almost 2 million public Twitter posts related to same-sex marriage in the U.S. states over the course of 4 years starting from 2011. Among other findings, we find evidence of moral culture wars between ideologies and show that constituencies that express higher levels of emotion and have fewer actively engaged participants often precede legalization efforts that fail. From our measures, we build statistical models to predict the outcome of potential policy changes, with our best model achieving 87% accuracy. We also achieve accuracies of 70%, comparable to public opinion surveys, many months before a policy decision. We discuss how these analyses can augment traditional political science techniques as well as assist activists and policy analysts in understanding discussions on important issues at a population scale.

The Geography and Importance of Localness in Geotagged Social Media

“…As noted above, much of the research has adopted the localness assumption. For instance, this has occurred in work that seeks to describe diurnal patterns in sentiment [15], predict public health measures [9], and measure human mobility [5], among other studies (e.g., [1,8,50]). Below, we show through a case study on the work of Mitchell et al [32] what can occur if non-local VGI is filtered out of these studies.…”

“…Indeed, researchers in HCI (e.g., [1,9,45,50]), the social sciences (e.g., [10,14,21,39,46,51]), and even the natural sciences (e.g., [38,44,49]) now regularly use social media VGI to better understand phenomena of interest ranging from social unrest and emergencies [6,24,43] to disease tracking [22,27,42].…”

The dynamics of Twitter users’ gun narratives across major mass shooting events

“…Social media and public deliberation. Social media have become an important source for studying public's opinion on social events and political issues including gun control, same-sex marriage, racial inequality, immigration, and abortion (Benton et al, 2016;Brooker et al, 2015;De Choudhury et al, 2016;Zhang and Counts, 2015;Chung, Wei, et al, 2016). While many of these studies relied on quantitative analyses of social media content, characterized by, for example, psycholinguistic and textual features, others suggested that social media enable studies beyond quantitative opinion polling by looking into the richer social conversation and political deliberation process (Anstead and O'Loughlin, 2015).…”

Party Politics, Values and the Design of Social Media Services

“…Social computing and human-computer interaction researchers have extensively studied online spaces for political discussion. For example, they have conducted observational studies on political discussions in online space, such as explorations on social media discussions during elections [115] or discussions and engagement on platforms for civic engagement [1]. Other scholars have taken more design-oriented approaches, asking how online spaces could even further support political discussions.…”