Quarenteners vs. Cloroquiners: a framework to analyze the effect of political polarization on social distance stances
Resumo
The worldwide COVID-19 pandemic has struck people’s lives overnight. With an alarming contagious rate and no effective treatments or vaccines, it has evoked all sorts of reactions. In this paper, we propose a framework to analyze how political polarization affects groups’ behavior with opposed stances, using the Brazilian COVID polarized scenario as a case study. Two Twitter groups represent the pro/against social isolation stances referred to as Chloroquiners and Quarenteners. The framework encompasses: a) techniques to automatically infer from users political orientation, b) topic modeling to discover the homogeneity of concerns expressed by each group; c) network analysis and community detection to characterize their behavior as a social network group and d) analysis of linguistic characteristics to identify psychological aspects. Our main findings confirm that Cloroquiners are right-wing partisans, whereas Quarenteners are more related to the left-wing. The political polarization of Chloroquiners and Quarenteners influence the arguments of economy and life, and support/opposition to the president. As a group, the network of Chloroquiners is more closed and connected, and Quarenteners have a more diverse political engagement. In terms of psychological aspects, polarized groups come together on cognitive issues and negative emotions.
Referências
De Choudhury, M., Jhaver, S., Sugar, B., and Weber, I. Social media participation in an activist movement for racial equality. In Proc. of the 10th Intl. Conf. on Web and Social Media (ICWSM). pp. 92–101, 2016.
Demszky, D., Garg, N., Voigt, R., Zou, J., Shapiro, J., Gentzkow, M., and Jurafsky, D. Analyzing polarization in social media: Method and application to tweets on 21 mass shootings. In Proc. of the 2019 Conf. of the North American Chapter of the Association for Computational Ling.: Human Language Technologies. pp. 2970–3005, 2019.
Garimella, V. and Weber, I. A long-term analysis of polarization on twitter. In Proc. of the 11th Intl. Conf. on Web and Social Media (ICWSM). pp. 528–531, 2017.
Harb, J., Ebeling, R., and Becker, K. Exploring deep learning for the analysis of emotional reactions to terrorist events on twitter. Journal of Information and Data Management 10 (2): 97–115, 2019.
Ordun, C., Purushotham, S., and Raff, E. Exploratory analysis of covid-19 tweets using topic modeling, umap, and digraphs. arxiv:2005.03082, 2020.
Pennycook, G., McPhetres, J., Bago, B., and Rand, D. Predictors of attitudes and misperceptions about covid-19 in canada, the UK, and the USA. doi:10.31234/osf.io/zhjkp, 2020.
Röder, M., Both, A., and Hinneburg, A. Exploring the space of topic coherence measures. In Proceedings of the eighth ACM international conference on Web search and data mining. ACM, pp. 399–408, 2015.
Sha, H., Hasan, M. A., Mohler, G., and Brantingham, P. J. Dynamic topic modeling of the covid-19 twitter narrative among u.s. governors and cabinet executives. arxiv:2004.11692, 2020.
Slatcher, R., Chung, C., Pennebaker, J., and Stone, L. Winning words: Individual differences in linguistic style among u.s. presidential and vice presidential candidates. Journal of Research in Personality 41 (1): 63 – 75, 2007.
Tausczik, Y. R. and Pennebaker, J. W. The psychological meaning of words: Liwc and computerized text analysis methods. Journal of Language and Social Psychology 29 (1): 24–54, 2010.
