Detection of Stance in Tweets about Politics in the Brazilian Context

• William Christhie UFMG
• Julio C. S. Reis UFMG
• Fabrício Benevenuto UFMG
• Mirella M. Moro UFMG
• Virgílio Almeida UFMG

DOI: https://doi.org/10.5753/brasnam.2018.3583

Abstract

Opinions shared over the Web constitute big volumes of data. Moreover, they may contain stances that are expressed directly or indirectly. Hence, stance detection may help to define the polarity related to a target idea. Here, we present the characterization of a broad set of tweets in Portuguese about the 2018 Brazilian presidential race. Such a set serves as the basis for automatic stance detection through a semi-supervised approach. In our evaluation, we find clues on the presence of bots in the network. We also evaluate three classifiers with paired statistical test, and our results present F-Measure above 94%.

References

Araújo, M., Reis, J., Pereira, A., and Benevenuto, F. (2016). An Evaluation of Machine Translation for Multilingual Sentence-level Sentiment Analysis. In Proceedings of the ACM Symposium on Applied Computing, pages 1140–1145.

Bigonha, C., Cardoso, T. N. C., Moro, M. M., Gonçalves, M. A., and Almeida, V. A. F. (2012). Sentiment-based influence detection on twitter. Journal of the Brazilian Computer Society, 18(3):169–183.

Caetano, J. A. C., Lima, H. S. L., dos Santos Santos, M. F., and Marques-Neto, H. T. M.-N. (2017). Utilizando análise de sentimentos para definição da homofilia política dos usuários do Twitter durante a eleição presidencial americana de 2016. In BraSNAM - Brazilian Workshop on Social Network Analysis and Mining, pages 480–491.

Chen, Y.-C., Liu, Z.-Y., and Kao, H.-Y. (2017). Ikm at semeval-2017 task 8: Convolutional neural networks for stance detection and rumor verification. In International Workshop on Semantic Evaluation, pages 465–469.

Christen, P. (2006). A comparison of personal name matching: Techniques and practical issues. In IEEE International Conference on Data Mining, pages 290–294.

Dias, M. and Becker, K. (2016a). An Heuristics-Based, Weakly-Supervised Approach for Classification of Stance in Tweets. In IEEE/WIC/ACM International Conference on Web Intelligence, pages 73–80.

Dias, M. and Becker, K. (2016b). Detecção semi-supervisionada de posicionamento em tweets baseada em regras de sentimento. In SBBD - Simpósio Brasileiro de Bancos de Dados, pages 40–51.

Mohammad, S. M., Sobhani, P., and Kiritchenko, S. (2017). Stance and sentiment in tweets. TOIT, 17(3):26.

Mourad, S. S., Shawky, D. M., Fayed, H. A., and Badawi, A. H. (2018). Stance detection in tweets using a majority vote classifier. In International Conference on Advanced Machine Learning Technologies and Applications, pages 375–384.

Reis, J. C., Gonçalves, P., Araújo, M., Pereira, A. C., and Benevenuto, F. (2015). Uma abordagem multilıngue para análise de sentimentos. In BraSNAM - Brazilian Workshop on Social Network Analysis and Mining.

Shenoy, G. G., Dsouza, E. H., and Kübler, S. (2017). Performing stance detection on Twitter data using computational linguistics techniques. arXiv preprint arXiv:1703.02019.

Silva, L. S., do Amaral, D. C., and Moro, M. M. (2017). Uma avaliação de eficiência e eficácia da combinação de técnicas para deduplicação de dados. In SBBD - Simpósio Brasileiro de Bancos de Dados, pages 160–171.

Verona, L. V., Oliveira, J. O., and Campos, M. L. M. C. (2017). Métricas para análise de poder em redes sociais e sua aplicação nas doações de campanha para o senado federal brasileiro. In BraSNAM - Brazilian Workshop on Social Network Analysis and Mining, pages 544–554.

Witten, I. H., Frank, E., Hall, M. A., and Pal, C. J. (2016). Data Mining: Practical machine learning tools and techniques. Morgan Kaufmann.

Xu, X., Hu, F., Du, P., Wang, J., and Li, L. (2017). Efficient stance detection with latent feature. In APWeb-WAIM - First International Joint Conference on Web and Big Data, pages 21–30.