Skip to main content

Characterizing political bias and comments associated with news on Brazilian Facebook

Abstract

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.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21

Notes

  1. https://developers.facebook.com/docs/marketing-apis.

  2. https://www.facebook.com/business/.

  3. https://developers.facebook.com/docs/graph-api/.

  4. https://www.perspectiveapi.com.

  5. https://g1.globo.com/.

  6. https://developers.facebook.com/docs/marketing-apis/.

  7. https://www.facebook.com/ads/audience_insights.

  8. When a user creates a page, he can assign a pre-defined category to it.

  9. https://www.theguardian.com/world/2019/nov/08/lula-brazil-released-prison-supreme-court-ruling

  10. https://developers.perspectiveapi.com/s/about-the-api-attributes-and-languages.

  11. https://www.crowdtangle.com.

  12. In this work we ignore Care because it was not available in 2019 (Moers et al. 2018) .

  13. https://www.facebook.com/business/news/sharing-actions-on-stopping-hate.

  14. https://scikit-learn.org/stable/.

  15. http://sgt.joachims.org/.

  16. The confidence intervals were calculated using Fisher Z transformation as presented on: http://onlinestatbook.com/2/estimation/correlation_ci.html.

  17. https://www.mturk.com/.

  18. https://developers.facebook.com/terms/.

  19. https://www.nytimes.com/2019/11/08/world/americas/lula-brazil-supreme-court.html.

References

  • An J, Kwak H, Posegga O, Jungherr A (2019) Political discussions in homogeneous and cross-cutting communication spaces. In: Proceedings of the 13th international AAAI conference on web and social media. AAAI Press, pp 68–79

  • Araujo M, Mejova Y, Weber I, Benevenuto F (2017) Using Facebook ads audiences for global lifestyle disease surveillance: Promises and limitations. In: Proceedings of the 9th ACM on web science conference. Association for Computing Machinery, pp 253–257

  • Bakshy E, Messing S, Adamic LA (2015) Exposure to ideologically diverse news and opinion on Facebook. Science 348(6239):1130–1132

    MathSciNet  Article  Google Scholar 

  • Barros S, Carreiro R (2015) A discussão pública e as redes sociais online: o comentário de notícias no facebook. Fronteiras-estudos Midiáticos 17(2):174–185

    Article  Google Scholar 

  • Basile A, Caselli T, Nissim M (2017) Predicting controversial news using facebook reactions. In: Proceedings of the 4th Italian conference on computational linguistics. Accademia University Press, pp 12–17

  • Budak C, Goel S, Rao JM (2016) Fair and balanced? quantifying media bias through crowdsourced content analysis. Public Opin Quart 80(S1):250–271

    Article  Google Scholar 

  • Cohen J (1960) A coefficient of agreement for nominal scales. Educ Psychol Meas 20(1):37–46

    Article  Google Scholar 

  • Conover MD, Gonçalves B, Ratkiewicz J, Flammini A, Menczer F (2011) Predicting the political alignment of twitter users. In: Proceedings of the 2011 IEEE international conference on privacy, security, risk and trust and 2011 IEEE international conference on social computing. IEEE, pp 192–199

  • Cover T, Hart P (1967) Nearest neighbor pattern classification. IEEE Trans Inf Theory 13(1):21–27

    Article  Google Scholar 

  • ElSherief M, Nilizadeh S, Nguyen D, Vigna G, Belding E (2018) Peer to peer hate: hate speech instigators and their targets. In: Proceedings of the 12th international AAAI conference on web and social media. AAAI Press, pp 52–61

  • Floyd RW (1962) Algorithm 97: shortest path. Commun ACM 5(6):345

    Article  Google Scholar 

  • Ganter SA, Paulino FO (2020) Between attack and resilience: the ongoing institutionalization of independent digital journalism in brazil. Digit J pp 1–20

  • Giuntini FT, Ruiz LP, Kirchner LDF, Passarelli DA, Dos Reis MDJD, Campbell AT, Ueyama J (2019) How do i feel? Identifying emotional expressions on facebook reactions using clustering mechanism. IEEE Access 7:53909–53921

    Article  Google Scholar 

  • Guimarães SS, Reis JCS, Lima L, Ribeiro FN, Vasconcelos M, An J, Kwak H, Benevenuto F (2020a) Identifying and characterizing alternative news media on facebook. In: Proceedings of the 2020 IEEE/ACM international conference on advances in social networks analysis and mining, pp 448–452

  • Guimarães SS, Reis JCS, Ribeiro FN, Benevenuto F (2020b) Characterizing toxicity on facebook comments in Brazil. In: Proceedings of the Brazilian symposium on multimedia and the web. Association for Computing Machinery, pp 253–260

  • Haynes B (2018) Facebook retira do ar rede ligada ao mbl antes das eleições https://br.reuters.com/article/idBRKBN1KF1MI-OBRDN.Accessed 30 Sept 2020

  • Hille S, Bakker P (2014) Engaging the social news user: comments on news sites and facebook. J Pract 8(5):563–572

    Google Scholar 

  • Holt K (2018) Alternative media and the notion of anti-systemness: towards an analytical framework. Media Commun 6(4):49–57

    Article  Google Scholar 

  • Holt K, Ustad Figenschou T, Frischlich L (2019) Key dimensions of alternative news media. Digit J 7(7):860–869

    Google Scholar 

  • Joachims T (2003) Transductive learning via spectral graph partitioning. In: Proceedings of the 20th international conference on machine learning. AAAI Press, pp 290–297

  • Kelkar S (2019) Post-truth and the search for objectivity: political polarization and the remaking of knowledge production. Engag Sci Technol Soc 5:86–106

    Article  Google Scholar 

  • Khan SA, Chang HT (2019) Comparative analysis on facebook post interaction using DNN, ELM and LSTM. PLoS ONE 14(11):1–26

    Article  Google Scholar 

  • Kolhatkar V, Taboada M (2017) Constructive language in news comments. In: Proceedings of the first workshop on abusive language online. Association for Computational Linguistics, pp 11–17

  • Lloyd S (1982) Least squares quantization in PCM. IEEE Trans Inf Theory 28(2):129–137

    MathSciNet  Article  Google Scholar 

  • Makazhanov A, Rafiei D (2013) Predicting political preference of twitter users. In: Proceedings of the 2013 IEEE/ACM international conference on advances in social networks analysis and mining. Association for Computing Machinery, 298–305

  • Mann HB, Whitney DR (1947) On a test of whether one of 2 random variables is stochastically larger than the other. Ann Math Stat 18(1):50–60

    MathSciNet  Article  Google Scholar 

  • Mitchell A, Gottfried J, Kiley J, Matsa KE (2014) Political polarization & media habits. https://www.pewresearch.org/journalism/2014/10/21/political-polarization-media-habits/. Accessed 15 Dec 2019

  • Moers T, Krebs F, Spanakis G (2018) Semtec: social emotion mining techniques for analysis and prediction of facebook post reactions. In: Proceedings of the 10th international conference on agents and artificial intelligence. Springer International Publishing, pp 361–382

  • Moretto M, Ortellado P (2018) Quanto mais velhos, mais polarizados: Perfil dos usuários que interagem com páginas de notícias no facebook. Tech. Rep. 1, Monitor do Debate Político no Meio Digital

  • Newman N (2011) Mainstream media and the distribution of news in the age of social media. RISJ Report 2011, Reuters Institute for the Study of Journalism

  • Newman N, Fletcher R, Kalogeropoulos A, Nielsen R (2019) Reuters Institute digital news report 2019. Reuters Institute for the Study of Journalism

  • de Pelle RP, Moreira VP (2017) Offensive comments in the Brazilian web: a dataset and baseline results. In: Proceedings of the 6th Brazilian workshop on social network analysis and mining. SBC, pp 510–519

  • Reis J, Benevenuto F, Vaz de Melo P, Prates R, Kwak H, An J (2015) Breaking the news: first impressions matter on online news. In: Proceedings of the 9th international AAAI conference on web-blogs and social media. AAAI Press, pp 357–366

  • Ribeiro FN, Henrique L, Benevenuto F, Chakraborty A, Kulshrestha J, Babaei M, Gummadi KP (2018) Media bias monitor: quantifying biases of social media news outlets at large-scale. In: Proceedings of the 12th international AAAI conference on web and social media. AAAI Press, pp 290—-299

  • Ribeiro FN, Kansaon D, Benevenuto F (2019) Leveraging the facebook ads platform for election polling. In: Proceedings of the 25th Brazilian symposium on multimedia and the web. Association for Computing Machinery, pp 305–312

  • Ribeiro FN, Benevenuto F, Zagheni E (2020) How biased is the population of facebook users? Comparing the demographics of facebook users and census data to generate correction factors. In: Proceedings of the 12th ACM web science conference. Association for Computing Machinery, pp 325–334

  • Rousseeuw PJ (1987) Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J Comput Appl Math 20:53–65

    Article  Google Scholar 

  • Russell A (2011) The Arab Spring| extra-national information flows, social media and the 2011 Egyptian uprising. Int J Commun 5:10

    Google Scholar 

  • Shearer E (2018) Social media outpaces print newspapers in the US as a news source. https://www.pewresearch.org/fact-tank/2018/12/10/social-media-outpaces-print-newspapers-in-the-u-s-as-a-news-source/. Accessed 15 Dec 2019

  • Shearer E, Matsa KE (2018) News use across social media platforms 2018 https://www.journalism.org/2018/09/10/news-use-across-social-media-platforms-2018/.Accessed 15 Dec 2019

  • Shi Y, Mast K, Weber I, Kellum A, Macy M (2017) Cultural fault lines and political polarization. In: Proceedings of the 9th ACM on web science conference. Association for Computing Machinery, pp 213–217

  • Starbird K (2017) Examining the alternative media ecosystem through the production of alternative narratives of mass shooting events on twitter. In: Proceedings of the 11th international AAAI conference on web and social media. AAAI Press, pp 230–239

  • Stroud NJ, Van Duyn E, Peacock C (2016) Survey of commenters and comment readers https://mediaengagement.org/research/survey-of-commenters-and-comment-readers/. Accessed 21 Feb 2020

  • Su LYF, Xenos MA, Rose KM, Wirz C, Scheufele DA, Brossard D (2018) Uncivil and personal? Comparing patterns of incivility in comments on the facebook pages of news outlets. New Media Soc 20(10):3678–3699

    Article  Google Scholar 

  • Thorndike RL (1953) Who belongs in the family? Psychometrika 18(4):267–276

    Article  Google Scholar 

  • Tian Y, Galery T, Dulcinati G, Molimpakis E, Sun C (2017) Facebook sentiment: reactions and emojis. In: Proceedings of the fifth international workshop on natural language processing for social media. Association for Computational Linguistics, pp 11–16

  • Toledo LF (2018) Maior rede pró-bolsonaro do facebook é excluída após denúncia do ‘estado’. https://politica.estadao.com.br/noticias/eleicoes,maior-rede-pro-bolsonaro-do-facebook-e-excluida-apos-denuncia-do-estado,70002558430. Accessed 15 May 2020

  • Vieira C, Ribeiro F, Vaz de Melo PO, Benevenuto F, Zagheni E (2020) Using facebook data to measure cultural distance between countries: the case of Brazilian cuisine. In: Proceedings of the web conference 2020. Association for Computing Machinery, pp 3091–3097

  • Weeks BE, Holbert RL (2013) Predicting dissemination of news content in social media: a focus on reception, friending, and partisanship. J Mass Commun Quart 90(2):212–232

    Google Scholar 

  • Wells C, Zhang Y, Lukito J, Pevehouse JCW (2020) Modeling the formation of attentive publics in social media: the case of Donald Trump. Mass Commun Soc 23(2):181–205. https://doi.org/10.1080/15205436.2019.1690664

    Article  Google Scholar 

  • Zhou D, Bousquet O, Lal TN, Weston J, Schölkopf B (2003) Learning with local and global consistency. In: Proceedings of the 16th international conference on neural information processing systems. MIT Press, pp 321–328

  • Zhu X, Ghahramani Z, Lafferty JD (2003) Semi-supervised learning using gaussian fields and harmonic functions. In: Proceedings of the 20th international conference on machine learning. AAAI Press, pp 912–919

Download references

Acknowledgements

This work was partially supported by the Ministério Público de Minas Gerais (MPMG), project Analytical Capabilities, as well as grants from CNPq, CAPES, and Fapemig.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Samuel S. Guimarães.

Ethics declarations

Conflict of interest:

The authors declare that they have no conflict of interest.

Availability of data and materials:

The datasets generated during and/or analyzed during the current study are available from the corresponding author on reasonable request.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Guimarães, S.S., Reis, J.C.S., Vasconcelos, M. et al. Characterizing political bias and comments associated with news on Brazilian Facebook. Soc. Netw. Anal. Min. 11, 94 (2021). https://doi.org/10.1007/s13278-021-00806-3

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s13278-021-00806-3

Keywords

  • Alternative media
  • Political bias
  • Toxicity
  • News ecosystem
  • Social computing
  • Machine learning