Quantifying Social Media’s Political Space: Estimating Ideology from Publicly Revealed Preferences on Facebook

Abstract

M any theories in political science rely on ideology at their core, whether they are explanations for individual behavior and preferences, governmental relations, or links between them. However, ideology has proven difficult to explicate and measure, in large part because it is impossible to directly observe: we can only examine indicators such as responses to survey questions, political donations, votes, and judicial decisions. One problem with this patchwork of indicator measures is the difficulty of studying ideology across domains. Although we have established reliable techniques for measuring ideology among individuals and legislators, such as survey measures and roll-call vote analysis, methods for jointly estimating the ideologies of ordinary citizens and elite actors have only recently been developed.To understand the relationship between elite ideology and beliefs of ordinary citizens, we need measures of ideology that allow us to place ordinary citizens and elites in the same ideological space. For example, a longstanding debate in political science concerns whether the American public has become more ideologically polarized in the last 40 years (e.g., Abramowitz and Saunders 2008;Fiorina, Abrams, and Pope 2006). If so, does mass polarization drive elite polarization, or vice versa? To test these theories, we need joint ideology measures that put elite actors and ordinary citizens on the same scale.

Search bias quantification: investigating political bias in social media and web search

“…Zafar et al (2016), have quantified the impartiality of social media posts by measuring how easy it is to guess the political leaning of its author. Bond and Messing (2015) inferred the political leanings of Facebook users by observing the endorsements of Facebook Pages of known politicians, while Wong et al (2016) measure the endorsements in terms of retweeting behavior of users to infer their political leanings. Cohen and Ruths (2013) used supervised methods to classify users into different groups of political activities and showed that it is hard to infer the political leaning of "normal" users.…”

“…Also, in Sect. 2, we have briefly described prior work which has developed techniques for measuring the bias of users (Purver and Karolina 2015;Makazhanov and Rafiei 2013;Fang et al 2015;Golbeck and Hansen 2011;Conover et al 2011a, b;Pennacchiotti and Popescu 2011;Bond and Messing 2015;Wong et al 2016) or content (Zafar et al 2016;Weber et al 2013) on social media as well as blogs and news stories (Adamic and Glance 2005;Yano et al 2010;Zhou et al 2011;Budak et al 2016;Munson et al 2013b) on the Web. In the future, when bias quantification schemes are developed for other search systems, for instance for videos (e.g., Youtube search) or music (e.g., Spotify), these methodologies can be plugged into our bias quantification framework and be used to analyze the bias of these other search systems.…”

Intra-party politics in 140 characters

“…As long as users publish online information on their tastes and opinions, several scholars suggest that the analysis of social media allows to scale-on an ideological axis-the position of citizens and politicians. These studies adopt two different methodologies: some of them follow a network approach (Barberá, 2015;Bond and Messing, 2015;Ecker, 2015;Hanretty, 2011;King et al, 2011;Livne et al, 2011), while others focus on the content of social media posts (Boireau, 2014;Boutet et al, 2013;Conover et al, 2011;Livne et al, 2011;Sylwester and Purver, 2015).…”

Politics on the Web: Using Twitter to Estimate the Ideological Positions of Brazilian Representatives

“…Despite these findings, they defend their own method because of its computation speed, as it could be used for a real time estimation process. Bond and Messing (2015) use Facebook data to estimate ideology. They estimate the political inclination of more than 1,223 political pages on this social network and then use their estimates to produce an individual estimate for profiles that follow these pages.…”