Abstract
This paper presents the study and comparison of methods of different paradigms to perform subjectivity classification of sentences in Portuguese. This task is part of the sentiment analysis area and consists of automatically identifying the presence or not of opinative information in texts of interest. We have investigated methods based on sentiment lexicons, graphs, machine learning and word embeddings, using datasets of different domains. We achieve good results, outperforming the previous approaches for Portuguese.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Avanço, L.V., Nunes, M.G.V.: Lexicon-based sentiment analysis for reviews of products in Brazilian Portuguese. In: The Proceedings of the 3rd Brazilian Conference on Intelligent Systems (BRACIS), pp. 277–281 (2014)
Bertaglia, T.F.P., Nunes, M.G.V.: Exploring word embeddings for unsupervised textual user-generated content normalization. In: The Proceedings of the 2nd Workshop on Noisy User-generated Text (WNUT), pp. 112–120 (2016)
Carvalho, P., Silva, M.J.: SentiLex-PT: Principais Características e Potencialidades. Oslo Stud. Lang. 7(1), 425–438 (2015)
Freitas, C., Motta, E., Milidiú, R., Cesar, J.: Vampiro que brilha… rá! Desafios na anotação de opinião em um corpus de resenhas de livros. In: The Proceedings of the XI Encontro de Linguística de Corpus (ELC), pp. 1–12 (2012)
Hartmann, N.S., et al.: A large opinion corpus in Portuguese - tackling out-of-vocabulary words. In: The Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC), pp. 3865–3871 (2014)
Liu, B.: Sentiment analysis and opinion mining. Synth. Lect. Hum. Lang. Technol. 5, 168 (2012)
López Condori, R.E., Pardo, T.A.S.: Opinion summarization methods: comparing and extending extractive and abstractive approaches. Expert Syst. Appl. (ESWA) 78, 124–134 (2017)
Maziero, E.G., Hirst, G., Pardo, T.A.S.: Adaptation of discourse parsing models for Portuguese language. In: The Proceedings of the 4th Brazilian Conference on Intelligent Systems - BRACIS, pp. 140–145 (2015)
Maziero, E.G., Hirst, G., Pardo, T.A.S.: Semi-supervised never-ending learning in rhetorical relation identification. In: The Proceedings of the Recent Advances in Natural Language Processing - RANLP, pp. 436–442 (2015)
Mikolov, T., Corrado, G., Chen, K., Dean, J.: Efficient estimation of word representations in vector space, pp. 1–12. arXiv:1301.3781 (2013)
Moraes, S.M.W., Santos, A.L.L., Redecker, M., Machado, R.M., Meneguzzi, F.R.: Comparing approaches to subjectivity classification: a study on Portuguese Tweets. In: Silva, J., Ribeiro, R., Quaresma, P., Adami, A., Branco, A. (eds.) PROPOR 2016. LNCS (LNAI), vol. 9727, pp. 86–94. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-41552-9_8
Pasqualotti, P.R., Vieira, R.: WordnetAffectBR: uma base lexical de palavras de emoções para a língua portuguesa. Revista Novas Tecnologias na Educação 6(2), 1–10 (2008)
Vilarinho, G.N., Ruiz, E.E.S.: Global centrality measures in word graphs for Twitter sentiment analysis. In: The Proceedings of the 7th Brazilian Conference on Intelligent Systems (BRACIS), pp. 55–60 (2018)
Yang, J., Liu, Y., Zhu, X., Liu, Z., Zhang, X.: A new feature selection based on comprehensive measurement both in inter-category and intra-category for text categorization. Inf. Process. Manage. 48(4), 741–754 (2012)
Acknowledgments
The authors are grateful to FAPESP (2018/11479-9) and USP Research Office (PRP 668) for supporting this work.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Belisário, L.B., Ferreira, L.G., Pardo, T.A.S. (2020). Evaluating Methods of Different Paradigms for Subjectivity Classification in Portuguese. In: Quaresma, P., Vieira, R., Aluísio, S., Moniz, H., Batista, F., Gonçalves, T. (eds) Computational Processing of the Portuguese Language. PROPOR 2020. Lecture Notes in Computer Science(), vol 12037. Springer, Cham. https://doi.org/10.1007/978-3-030-41505-1_25
Download citation
DOI: https://doi.org/10.1007/978-3-030-41505-1_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-41504-4
Online ISBN: 978-3-030-41505-1
eBook Packages: Computer ScienceComputer Science (R0)