Sentiment Analysis of Tweets in Brazilian Portuguese with Convolutional Neural Networks

Juan Manuel Adán Coello; Armando  Dalla Costa Neto

doi:10.31686/ijier.vol7.iss6.1547

Authors

Juan Manuel Adán Coello Pontifícia Universidade Católica de Campinas (PUC-Campinas) Brazil
Armando Dalla Costa Neto PUC-Campinas

DOI:

https://doi.org/10.31686/ijier.vol7.iss6.1547

Keywords:

opinion mining, deep learning, Brazilian Portuguese

Abstract

Sentiment analysis of texts posted on Twitter is a natural language processing task whose importance has grown along with the increase in the number of users of the platform and the interest of organizations on the opinions of their employees, customers and users.Although Brazil is the sixth country in the world with most active users of Tweeter and Portuguese is the seventh most spoken language in the world, with 221 million speakers (200 million of them living in Brazil), the number of articles that discuss sentiment analysis approaches for Brazilian Portuguese is a small fraction of those that focus on the English language. On the other hand, few works use deep learning for this task when compared with other machine learning and lexical based methods. In this context, the work described in this article addresses the problem using Convolutional Neural Networks (CNN). The paper presents the results of an experimental evaluation that shows that a CNN with a relatively simple architecture can perform much better than a previous approach that uses ensembles of other machine learning classifiers combined with text preprocessing heuristics

Downloads

Download data is not yet available.

References

[1] Kim, Y.: Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882. (2014).

[2] Zhang, Y., Wallace, B.: A Sensitivity Analysis of (and Practitioners’ Guide to) Convolutional Neural Networks for Sentence Classification. In: Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers). pp. 253–263 (2017).

[3] Corrêa, E.A., Marinho, V.Q., dos Santos, L.B., Bertaglia, T.F.C., Treviso, M.V., Brum, H.B.: PELESent: Cross-domain polarity classification using distant supervision. In: 2017 Brazilian Conference on Intelligent Systems (BRACIS). pp. 49–54. IEEE (2017).

[4] Brum, H.B., Nunes, M. das G.V.: Building a Sentiment Corpus of Tweets in Brazilian Portuguese. In: Proceedings of the Eleventh International Conference on Language Re-sources and Evaluation (LREC 2018), Miyazaki, Japan (2018).

[5] Gomes, F.B., Adán-Coello, J.M., Kintschner, F.E.: Studying the Effects of Text Preprocessing and Ensemble Methods on Sentiment Analysis of Brazilian Portuguese Tweets. In: International Conference on Statistical Language and Speech Processing. pp. 167–177. Springer (2018).

[6] Go, A., Bhayani, R., Huang, L.: Twitter sentiment classification using distant supervision. CS224N Project Report, Stanford. 1, (2009).

[7] Teh, P.L., Rayson, P., Pak, I., Piao, S., Yeng, S.M.: Reversing the polarity with emoti-cons. In: International Conference on Applications of Natural Language to Information Systems. pp. 453–458. Springer (2016).

[8] Jacovi, A., Shalom, O.S., Goldberg, Y.: Understanding Convolutional Neural Networks for Text Classification. In: Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP. pp. 56–65 (2018).

[9] S. Rosenthal, N. Farra, e P. Nakov, “SemEval-2017 task 4: Sentiment analysis in Twitter”, in Proceedings of the 11th international workshop on semantic evaluation (SemEval-2017), 2017, p. 502–518.

[10] M. Cliche, “BB_twtr at SemEval-2017 task 4: twitter sentiment analysis with CNNs and LSTMs”, arXiv preprint arXiv:1704.06125, 2017.

[11] Cirqueira, D., Jacob, A., Lobato, F., de Santana, A.L., Pinheiro, M.: Performance evaluation of sentiment analysis methods for Brazilian Portuguese. In: International Conference on Business Information Systems. pp. 245–251. Springer (2016).

[12] Prata, D.N., Soares, K.P., Silva, M.A., Trevisan, D.Q., Letouze, P.: Social Data Analysis of Brazilian’s Mood from Twitter. International Journal of Social Science and Humanity. 6, 179 (2016).

[13] Souza, E., Vitório, D., Castro, D., Oliveira, A.L., Gusmão, C.: Characterizing Opinion Mining: A Systematic Mapping Study of the Portuguese Language. In: International Conference on Computational Processing of the Portuguese Language. pp. 122–127. Springer (2016).

[14] Wehrmann, J., Becker, W., Cagnini, H.E., Barros, R.C.: A character-based convolutional neural network for language-agnostic Twitter sentiment analysis. In: 2017 International Joint Conference on Neural Networks (IJCNN). pp. 2384–2391. IEEE (2017).

[15] Araujo, G.D. de, Teixeira, F.O., Mancini, F., Guimarães, M. de P., Pisa, I.T.: Sentiment Analysis of Twitter’s Health Messages in Brazilian Portuguese. Journal of Health Informatics. 10, (2018).