Measuring Network Polarization and Political Sectarianism During the 2020 Pandemic

Autor(es):Mostrar menos -

Kamienski, Carlos ; de Camargo Penteado, Claudio Luis ; Goya, Denise ; Rocha, Rafaela, V ; de Souza, Lucas Mazim ; Beraldo di Genova, Daniel Vitor ; Segura Ramos, Diogo Fornaziero ; de Franca, Fabricio Olivetti ; Horita, Flavio ; dos Santos, Carlos da Silva ; Kamienski, Carlos Alberto

• Tipo de documento: Artigo Científico
• Fonte: IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS; v. N/A, p. 16-pg., 2022-03-25.

Resumo

Online social networks are at the limelight of the public debate, where antagonistic groups compete to impose conflicting narratives and polarize the discussions. This article proposes an approach for measuring network polarization and political sectarianism in Twitter based on user interaction networks. Centrality metrics identify a small group of influential users (polarizers and unpolarizers) who influence a larger group of users (polarizees and unpolarizees) according to their ideological stance (left, right, and undefined). This network polarization is computed by the Bayesian probability using typical actions such as following, tweeting, retweeting, and replying. The measurement of political sectarianism also uses Bayesian probability and words extracted from the tweets to quantify the intensity of othering, aversion, and moralization in the debate. We collected Twitter data from 33 conflicted political events in Brazil during 2020, strongly influenced by the COVID-19 pandemic. Based on our methodology and polarization score, our results reveal that the approach based on user interaction networks leads to an increasing understanding of polarized conflicts in Twitter. Also, a small number of polarizers is enough to represent the polarization and sectarianism of Twitter events. (AU)

• Processo FAPESP: 18/23022-3 - Observatório de conflitos na internet
• Beneficiário: Carlos Alberto Kamienski
• Modalidade de apoio: Auxílio à Pesquisa - Regular