Characterizing political bias and comments associated with news on Brazilian Facebook

• Published in: Social network analysis and mining Vol. 11; no. 1; p. 94
• Main Authors: Guimarães, Samuel S., Reis, Julio C. S., Vasconcelos, Marisa, Benevenuto, Fabrício
• Format: Journal Article
• Language: English
• Published: Vienna Springer Vienna 01.12.2021; Springer Nature B.V
• Subjects: Applications of Graph Theory and Complex Networks; Audiences; Bias; Computer Science; Data Mining and Knowledge Discovery; Dissemination; Economics; Ecosystems; Game Theory; Graphs; Humanities; Ideology; Information dissemination; Interest groups; Journalism; Law; Methodology of the Social Sciences; News; Original Article; Political activism; Political attitudes; Public figures; Social and Behav. Sciences; Social media; Social networks; Statistics for Social Sciences; Toxicity; Brazil; United States > US; Alternative media; Social computing; News ecosystem; Toxicity; Machine learning; Political bias
• ISSN: 1869-5450; 1869-5469
• DOI: 10.1007/s13278-021-00806-3

Social media sites became an important channel to consume information, including news articles. In this context, there are a growing number of outlets that present themselves as news sources. However, among these outlets, we may have people objectively presenting reliable information or a political group acting in bad faith. Their actions can even provoke different kinds of hateful responses from their audience, in the form of toxic comments. Therefore, identifying and characterizing all the news pages that play a vital role in information dissemination is essential for understanding this media ecosystem in a country. This work provides a detailed diagnostic of news stories and political opinions shared on Facebook, focusing on Brazilian pages. We present as main contributions: (1) a methodology to identify and measure the political bias of Facebook pages for a given country and (2) an in-depth characterization of the political bias, audience demographics, reactions in posts, and toxicity of the comments of a sample of mainstream media, alternative media, and public figures.