Abstract
This work presents an analysis of Brazilian political discourse from speeches and social media posts, focusing on the ability to transfer learned models’ knowledge between different contexts. The analysis is conducted through PoliS, a new resource containing two datasets of political discussions labeled for party and ideological leaning from congressional speeches and social media posts by political influencers. The transfer learning experiments are performed using the transcripts of the congressional speeches to train a model used to predict the political leaning of social media influencers. To evaluate the robustness of the model, the analysis includes a time-lag study of the performance degradation of the transferred model. We find that relatively little social media data (about one hour) is needed to achieve reasonable performance in classification, and that performance does not degrade significantly over time.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Barberá, P., Jost, J.T., Nagler, J., Tucker, J.A., Bonneau, R.: Tweeting from left to right: is online political communication more than an echo chamber? Psychol. Sci. 26(10), 1531–1542 (2015). https://doi.org/10.1177/0956797615594620
Boser, B.E., Guyon, I.M., Vapnik, V.N.: A training algorithm for optimal margin classifiers. In: Proceedings of the Annual Workshop on Computational Learning Theory, pp. 144–152. Association for Computing Machinery, New York (1992). https://doi.org/10.1145/130385.130401
Brito, K., Paula, N., Fernandes, M., Meira, S.: Social media and presidential campaigns - preliminary results of the 2018 Brazilian Presidential Election. In: Proceedings of the 20th Annual International Conference on Digital Government Research, pp. 332–341. dg.o 2019, Association for Computing Machinery, New York (2019). https://doi.org/10.1145/3325112.3325252
Colliri, T., Zhao, L.: Analyzing the bills-voting dynamics and predicting corruption-convictions among Brazilian congressmen through temporal networks. Sci. Rep. 9(1), 1–11 (2019). https://doi.org/10.1038/s41598-019-53252-9
Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995). https://doi.org/10.1007/BF00994018
Demszky, D., et al.: Analyzing polarization in social media: method and application to tweets on 21 mass shootings. In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 2970–3005. Association for Computational Linguistics, Minneapolis (2019). https://doi.org/10.18653/v1/N19-1304
Gilardi, F., Gessler, T., Kubli, M., Müller, S.: Social media and political agenda setting. Polit. Commun. 39(1), 39–60 (2021). https://doi.org/10.1080/10584609.2021.1910390
Hartmann, N.S., Fonseca, E.R., Shulby, C.D., Treviso, M.V., Rodrigues, J.S., Aluísio, S.M.: Portuguese word embeddings: evaluating on word analogies and natural language tasks. In: Anais do Simpósio Brasileiro de Tecnologia da Informação e da Linguagem Humana, pp. 122–131. SBC, Porto Alegre (2017)
Haykin, S.S.: Neural Networks and Learning Machines, 3rd edn. Pearson Education, Upper Saddle River (2009)
Johnson, K., Goldwasser, D.: Classification of moral foundations in microblog political discourse. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics, pp. 720–730. Association for Computational Linguistics, Melbourne (2018). https://doi.org/10.18653/v1/P18-1067
Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, vol. 26, pp. 3111–3119. Curran Associates, Inc. (2013). https://doi.org/10.5555/2999792.2999959
Peterson, A., Spirling, A.: Classification accuracy as a substantive quantity of interest: measuring polarization in westminster systems. Polit. Anal. 26(1), 120–128 (2018). https://doi.org/10.1017/pan.2017.39
Recuero, R., Soares, F.B., Gruzd, A.: Hyperpartisanship, disinformation and political conversations on Twitter: the Brazilian Presidential Election of 2018. In: Proceedings of the International AAAI Conference on Web and Social Media, vol. 14, no. 1, pp. 569–578 (2020)
Sales, A., Balby, L., Veloso, A.: Media bias characterization in Brazilian Presidential Elections. In: Proceedings of the ACM Conference on Hypertext and Social Media, pp. 231–240. Association for Computing Machinery, New York (2019). https://doi.org/10.1145/3342220.3343656
Sardinha, E., Costa, S.: Direita cresce e engole o centro no Congresso mais fragmentado da história. Congresso em Foco (2019). https://bit.ly/3jwMbc8
Shalders, A.: Direita ou esquerda? Análise de votações indica posição de partidos brasileiros no espectro ideológico. BBC Brasil (2017). https://bbc.in/3noEkOR
de Souza, R.M., Guedes da Graça, L.F., dos Santos Silva, R.: Politics on the web: using Twitter to estimate the ideological positions of Brazilian representatives. Braz. Polit. Sci. Rev. 11, 1–26 (2017)
Tsakalidis, A., Aletras, N., Cristea, A.I., Liakata, M.: Nowcasting the stance of social media users in a sudden vote: the case of the Greek Referendum. In: Proceedings of the ACM International Conference on Information and Knowledge Management, pp. 367–376. Association for Computing Machinery, New York (2018). https://doi.org/10.1145/3269206.3271783
Tsur, O., Calacci, D., Lazer, D.: A frame of mind: using statistical models for detection of framing and agenda setting campaigns. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics and the International Joint Conference on Natural Language Processing, pp. 1629–1638 (2015)
Vasconcellos, F.: Maioria dos partidos se posiciona como de Centro. Veja quem sobra no campo da Direita e da Esquerda. O Globo (2016). https://glo.bo/3BaP6gj
Yu, H.F., Huang, F.L., Lin, C.J.: Dual coordinate descent methods for logistic regression and maximum entropy models. Mach. Learn. 85(1–2), 41–75 (2011). https://doi.org/10.1007/s10994-010-5221-8
Zhou, P., et al.: Attention-based bidirectional long short-term memory networks for relation classification. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics, pp. 207–212. Association for Computational Linguistics, Berlin (2016). https://doi.org/10.18653/v1/P16-2034
Acknowledgment
This work was supported by Portuguese national funds through Fundação para a Ciência e a Tecnologia (FCT) under references UIDB/50021/2020 and SFRH/BD/145561/2019.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Caled, D., Silva, M.J. (2022). A Transfer Learning Analysis of Political Leaning Classification in Cross-domain Content. In: Pinheiro, V., et al. Computational Processing of the Portuguese Language. PROPOR 2022. Lecture Notes in Computer Science(), vol 13208. Springer, Cham. https://doi.org/10.1007/978-3-030-98305-5_25
Download citation
DOI: https://doi.org/10.1007/978-3-030-98305-5_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-98304-8
Online ISBN: 978-3-030-98305-5
eBook Packages: Computer ScienceComputer Science (R0)