Machine learning for cross-platform political communication research: Argentine government and opposition in Facebook, Instagram and Twitter

Authors

DOI:

https://doi.org/10.7764/cdi.55.52631

Keywords:

social media, Twitter, Instagram, Facebook, Argentina, politics, natural language processing, topic modeling

Abstract

This article studies political communication in different platforms, applying data science methods to analyze similarities and differences among Facebook, Instagram, and Twitter posts of 50 Argentinian politicians in 2020. This is a pioneering cross-platform study for our region, and its objectives are heuristic and methodological. Regarding the former, we show that strategies differ among platforms: Twitter is the battlefield for controversy and interpellations among politicians, and toxicity is rewarded, while on Facebook and Instagram politicians expand on the topics in which they seem to consider themselves stronger. The closs-platform study shows that even in a polarized context such as the Argentinean one, there are common and non-controversial topics. Methodologically, we use novel analytical methods and implemented a recent topic-detection algorithm, we apply sentiment analysis techniques to understand if texts have positive or negative intentions, and deep neural networks to detect toxicity in a text, among others. Readers are offered access to the toolbox developed during the research, which can be useful for working large text corpora.

Author Biographies

Federico Albanese, Instituto de Ciencias de la Computación, Universidad de Buenos Aires, Buenos Aires, Argentina

Federico Albanese, holds a degree in Computer Science from the Universidad de Buenos Aires, Ph.D. student in Computer Science at the same university, and member of the Institute of Computer Science (CONICET - UBA). He teaches in the master's program in Data Exploitation at the Faculty of Exact and Natural Sciences, UBA. His research is currently focused on the study of machine learning models in graphs and their applications to social networks.

Esteban Feuerstein, Instituto de Ciencias de la Computación, Universidad de Buenos Aires, Buenos Aires, Argentina

Esteban Feuerstein, holds a degree in Computer Science from the Escuela Superior Latinoamericana de Informática (ESLAI) and a Ph.D. in Computer Science from the University of Rome La Sapienza. He has more than 25 years of experience as a researcher and consultant in public and private organizations. He is an associate professor in the Department of Computer Science at the Faculty of Exact and Natural Sciences (UBA). His area of expertise is in the field of algorithms and data structures, and the search and organization of information and big data.

Gabriel Kessler, Universidad Nacional de La Plata, La Platay Universidad Nacional de San Martín, San Martín, Argentina

Gabriel Kessler, Ph.D. in Sociology from EHESS-Paris, CONICET researcher and professor at the Universidad Nacional de La Plata and the Universidad Nacional de San Martín. His research areas are inequality, violence, and political polarization. He is the author of numerous books and academic articles. His latest books are (with Gabriela Benza) Uneven Trajectories. Latin America Societies in the XXI Century (Cambridge University Press, 2020) and La ¿Nueva? estructura social de América Latina (Latin America’s New (?) Social Structure) (Siglo XXI, 2021).

Juan Manuel Ortiz de Zárate, Instituto de Ciencias de la Computación, Universidad de Buenos Aires, Buenos Aires, Argentina

Juan Manuel Ortiz de Zárate, holds a degree in Computer Science from the Universidad de Buenos Aires, Ph.D. student in Computer Science at the same university, and member of the Institute of Computer Science (CONICET - UBA). With experience in both the academic and private sectors, his research is currently focused on the study of social networks through natural language processing and graph modeling.

References

Ain, Q. T., Ali, M., Riaz, A., Noureen, A., Kamran, M., Hayat, B., & Rehman, A. (2017). Sentiment Analysis Using Deep Learning Techniques: A Review. International Journal of Advanced Computer Science and Applications, 8(6). https://doi.org/10.14569/IJACSA.2017.080657

Angelov, D. (2020). Top2vec: Distributed Representations of Topics. arXiv preprint arXiv:2008.09470. https://doi.org/10.48550/arXiv.2008.09470

Ansolabehere, S. & Iyengar, S. (1994). Riding the wave and claiming ownership over issues: The joint effects of advertising and news coverage in campaigns. Public Opinion Quarterly, 58(3), 335-357. https://doi.org/10.1086/269431

Arcila Calderón, C., Van Atteveldt, W., & Trilling, D. (2021). Métodos Computacionales y Big Data en la Investigación en Comunicación: Editorial Dossier (Special Issue Computational Methods and Big Data in Communication Research ). Cuadernos.Info, (49), I-IV.

Aruguete, N. (2015). El poder de la agenda: política, medios y público (The power of the agenda: politics, media, and public). Biblos.

Bast, J. (2021). Managing the Image. The Visual Communication Strategy of European Right- Wing Populist Politicians on Instagram. Journal of Political Marketing. https://doi.org/10.1080/15377857.2021.1892901

Bishop, C. M. (2006). Pattern Recognition and Machine Learning. Springer. https://link.springer.com/book/9780387310732

Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent Dirichlet Allocation. Journal of Machine Learning Research, 3, 993-1022.https://jmlr.org/papers/v3/blei03a.html

Bossetta, M. (2018). The Digital Architectures of Social Media: Comparing Political Campaigning on Facebook, Twitter, Instagram, and Snapchat in the 2016 US Election. Journalism & Mass Communication Quarterly, 95(2), 471-496. https://doi.org/10.1177/1077699018763307

Calvo, E. (2015). Anatomía política de Twitter en Argentina. Tuiteando #Nisman (Political anatomy of Twitter in Argentina. Tweeting #Nisman). Capital Intelectual.

Calvo, E. & Aruguete, N. (2020). Fake news, trolls y otros encantos: Cómo funcionan (para bien y para mal) las redes sociales (Fake news, trolls, and other charms: How do social networks work (for better and for worse)). Siglo XXI Editores.

Cárdenas, A. (2020). Uso de Twitter como estrategia de comunicación política en campañas presidenciales (México, Colombia y Perú 2012-2016). Razón y Palabra, 24, (109). https://doi.org/10.26807/rp.v24i109.1716

Chadwick, A., Dennis, J., & Smith, A. P. (2015). Politics in the Age of Hybrid Media: Power, Systems, and Media Logics. In A. Bruns, G. Enli, E. Skogerbø, A. O. Larsson, & C. Christensen, The Routledge Companion to Social Media and Politics (pp. 7-22). Routledge.

Enli, G. S. & Skogerbø, E. (2013). Personalized campaigns in party-centred politics. Twitter and Facebook as arenas for political communication. Information, Communication & Society, 16(5), 757-774. https://doi.org/10.1080/1369118X.2013.782330

Figuereo-Benítez, J. C., González-Quiñones, F., & Machin-Mastromatteo, J. D. (2021). Instagram como objeto de estudio en investigaciones recientes. Una revisión de literatura con enfoque en revistas científicas (Instagram as an object of study in recent research. A literature review with a focus on scientific journals). Ámbitos: Revista internacional de comunicación, 53, 9-23. https://doi.org/10.12795/Ambitos.2021.i53.01

Flores-Márquez, D. & González Reyes, R. (2021). En busca de coordenadas metodológicas para estudiar la cultura digital (In search of methodological coordinates to study digital culture). In D. Flores-Márquez & R. González Reyes (Coords), La imaginación metodológica. Coordenadas, rutas y apuestas para el estudio de la cultura digital (The methodological imagination. Coordinates, routes, and stakes for the study of digital culture) (pp. 15-23). Tintable.

Fortuna, P., Soler, J., & Wanner, L. (2020, May). Toxic, Hateful, Offensive or Abusive? What Are We Really Classifying? An Empirical Analysis of Hate Speech Datasets. In Proceedings of the Twelfth Language Resources and Evaluation Conference (pp. 6786-6794). European Language Resources Association. https://aclanthology.org/2020.lrec-1.838

Garimella, K., Morales, G. D. F., Gionis, A., & Mathioudakis, M. (2018). Quantifying Controversy on Social Media. ACM Transactions on Social Computing, 1(1), 1-27. https://doi.org/10.1145/3140565

González-Bustamante, B. (2015). Evaluando Twitter como indicador de opinión pública: una mirada al arribo de Bachelet a la presidencial chilena 2013 (Assessing Twitter as an indicator of public opinion: a look at Bachelet’s arrival to the Chilean presidential election in 2013). Revista SAAP, 9(1), 119-141. https://revista.saap.org.ar/articulos/revista-saap-volumen-9-1.html

Gruzd, A., Lannigan, J., & Quigley, K. (2018). Examining government cross-platform engagement in social media: Instagram vs Twitter and the big lift project. Government Information Quarterly, 35(4), 579-587. https://doi.org/10.1016/j.giq.2018.09.005

Gusfield, J. R. (2014). La cultura de los problemas públicos: el mito del conductor alcoholizado versus la sociedad inocente (The culture of public problems: the myth of the drunk driver versus the innocent society). Siglo XXI Editores.

Hasebrink, U. & Hepp, A. (2017). How to research cross-media practices? Investigating media repertoires and media ensembles. Convergence: The International Journal of Research into New Media Technologies, 23(4), 362-377. https://doi.org/10.1177/1354856517700384

Hodges, J. L. (1958). The significance probability of the smirnov two-sample test. Arkiv för Matematik, 3(5), 469-486. https://doi.org/10.1007/bf02589501

Hua, Y., Ristenpart, T., & Naaman, M. (2020). Towards Measuring Adversarial Twitter Interactions against Candidates in the US Midterm Elections. Proceedings of the International AAAI Conference on Web and Social Media, 14(1), 272-282. https://doi.org/10.1609/icwsm.v14i1.7298

Iyengar, S. (1990). The accessibility bias in politics: Television news and public opinion. International Journal of Public Opinion Research, 2(1), 1-15.

Jaidka, K., Guntuku, S., & Ungar, L. (2018, June). Facebook versus Twitter: Differences in self-disclosure and trait prediction. Proceedings of the International AAAI Conference on Web and Social Media, 12(1). https://doi.org/10.1609/icwsm.v12i1.15026

Kaplan, N., Park, D. K., & Ridout, T. N. (2006). Dialogue in American Political Campaigns? An Examination of Issue Convergence in Candidate Television Advertising. American Journal of Political Science, 50(3), 724-736. https://doi.org/10.1111/j.1540-5907.2006.00212.x

Karlsen, R. & Enjolras, B. (2016). Styles of Social Media Campaigning and Influence in a Hybrid Political Communication System: Linking Candidate Survey Data with Twitter Data. The International Journal of Press/Politics, 21(3), 338-357. https://doi.org/10.1177/1940161216645335

Kelley, S. & Mirer, T. W. (1974). The Simple Act of Voting. American Political Science Review, 68(2), 572-591. https://doi.org/10.2307/1959506

Larsson, A. O. (2015). Green light for interaction: Party use of social media during the 2014 Swedish election year. First Monday, 20(1). https://doi.org/10.5210/fm.v20i12.5966

LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., & Jackel, L. D. (1989). Backpropagation applied to handwritten zip code recognition. Neural Computation, 1(4), 541-551. https://doi.org/10.1162/neco.1989.1.4.541

López-López, P. C. & Vásquez-González, J. (2018). Agenda temática y Twitter: elecciones presidenciales en América Latina durante el período 2015-2017 (Thematic agenda and Twitter: Presidential elections in Latin America during the 2015-2017 period). Profesional De La Información, 27(6), 1204-1214. https://doi.org/10.3145/epi.2018.nov.04

Manning, C. & Schütze, H. (1999). Foundations of Statistical Natural Language Processing. MIT Press.

Martin, J. R. & White, P. R. R. (2005). The Language of Evaluation. Appraisal in English. Palgrave Macmillan.

McPherson, M., Smith-Lovin, L., & Cook, J. M. (2001). Birds of a Feather: Homophily in Social Networks. Annual Review of Sociology, 27, 415-444. https://doi.org/10.1146/annurev.soc.27.1.415

Müller, A. C. & Guido, S. (2016). Introduction to Machine Learning with Python. A Guide for Data Scientists.

O'Reilly Media, Inc. Nielsen, R. K. & Schrøder, K. C. (2014). The Relative Importance of Social Media for Accessing, Finding, and Engaging with News. An eight-country cross-media comparison. Digital Journalism, 2(4), 472-489. https://doi.org/10.1080/21670811.2013.872420

Owen, D. (2017). New Media and Political Campaigns. In K. Kensi & K. Hall Jamieson (Eds.), The Oxford Handbook of Political Communication (pp. 829-836). https://doi.org/10.1093/ oxfordhb/9780199793471.013.016

Paulino, F. O. & Waisbord, S. (2021). Las narrativas del populismo reaccionario: Bolsonaro en Twitter durante la pandemia (The narratives of reactionary populism: Bolsonaro on Twitter during the pandemic). Mediapolis–Revista de Comunicação, Jornalismo e Espaço Público, (12), 33-48. https://doi.org/10.14195/2183-6019_12_2

Petrocik, J. R. (1996). Issue Ownership in Presidential Elections, with a 1980 Case Study. American Journal of Political Science, 40(3), 825-850. https://doi.org/10.2307/2111797

Prada Espinel, Ó. A. & Romero Rodríguez, L. M. (2018). Polarización y demonización en la campaña presidencial de Colombia de 2018: análisis del comportamiento comunicacional en el Twitter de Gustavo Petro e Iván Duque (Polarization and Demonization in the 2018 Presidential Campaign of Colombia: Analysis of Twitter’s Communication Behavior by Gustavo Petro and Iván Duque). Revista Humanidades, 9(1). https://doi.org/10.15517/h.v9i1.35343

Quevedo, L. A., & Ramírez, I. (2022). Polarizados ¿Por qué preferimos la grieta?(Aunque digamos lo contrario). Revista SAAP, 16(1), 220-222.

Röder, M., Both, A., & Hinneburg, A. (2015). Exploring the Space of Topic Coherence Measures. In X. Cheng & H. Li (Chairs), WSDM’15: Proceedings of the Eighth ACM International Conference on Web Search and Data Mining (pp. 399-408). https://doi.org/10.1145/2684822.2685324

Rogers, R. (2017). Digital Methods for Cross-Platform Analysis. In J. Burgess, A. Marwick, & T. Poell, The SAGE Handbook of Social Media (pp. 91-110). SAGE. https://doi.org/10.4135/9781473984066

Salgado Andrade, E. (2013). Twitter en la campaña electoral de 2012 (Twitter in the Electora Campaign of 2012). Desacatos, (42), 217-232. https://doi.org/10.29340/42.78

Scheufele, D. A. (2000). Agenda-Setting, Priming, and Framing Revisited: Another Look at Cognitive Effects of Political Communication. Mass Communication & Society, 3(2-3), 297-316. https://doi.org/10.4324/9781315679402-5

Scheufele, D. A. & Iyengar, S. (2012). The State of Framing Research: A Call for New Directions. In K. Kenski & K. Hall Jamieson (Eds.), The Oxford Handbook of Political Communication Theories (pp. 1-26). https://doi.org/10.1093/oxfordhb/9780199793471.013.47

Spierings, N. & Jacobs, K. (2019). Political parties and social media campaigning. Acta Politica, 54(1), 145-173. https://doi.org/10.1057/s41269-018-0079-z

Stier, S., Bleier, A., Lietz, H., & Strohmaier, M. (2018). Election Campaigning on Social Media: Politicians, Audiences, and the Mediation of Political Communication on Facebook and Twitter. Political Communication, 35(1), 50-74. https://doi.org/10.1080/10584609.2017.1334728

Thelwall, M. (2017). The Heart and Soul of the Web? Sentiment Strength Detection in the Social Web with SentiStrength. In J. Holyst (Ed.), Cyberemotions. Understanding Complex Systems (pp. 119-134). Springer. https://doi.org/10.1007/978-3-319-43639-5_7

Thorhauge, A. M. & Lomborg, S. (2016). Cross-media communication in context: A mixedmethods approach. MedieKultur: Journal of Media and Communication Research, 32(60), 16. https://doi.org/10.7146/mediekultur.v32i60.22090

Wulczyn, E., Thain, N., & Dixon, L. (2017). Ex Machina: Personal Attacks Seen at Scale. In R. Barret & R. Cummings (Chairs), WWW’ 17: Proceedings of the 26th International Conference on World Wide Web (pp. 1391–1399). International World Wide Web Conferences Steering Committee. https://doi.org/10.1145/3038912.3052591

Zwillinger, D. & Kokoska, S (2000). CRC Standard Probability and Statistics Tables and Formulae. Champan & Hall.

Downloads

Published

2023-05-31

How to Cite

Albanese, F., Feuerstein, E. ., Kessler, G., & Ortiz de Zárate, J. M. (2023). Machine learning for cross-platform political communication research: Argentine government and opposition in Facebook, Instagram and Twitter. Cuadernos.Info, (55), 256–280. https://doi.org/10.7764/cdi.55.52631

Issue

No. 55 (2023): Temas Generales: En búsqueda de la identidad de las comunicaciones: la riqueza de una visión multifacética

Section

OTHER TOPICS

License

Copyright (c) 2023 Cuadernos.info

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.