Automatic Analysis of Facebook Posts and Comments Written in  Brazilian Portuguese

Juan Manuel Adán Coello; Bruno Augusto Junqueira

doi:10.31686/ijier.vol7.iss6.1553

Authors

Juan Manuel Adán Coello

Pontifícia Universidade Católica de Campinas (PUC-Campinas) Brazil
Bruno Augusto Junqueira

CI&T

DOI:

https://doi.org/10.31686/ijier.vol7.iss6.1553

Keywords:

Social networks, Text mining, Machine learning

Abstract

Social networks and media are becoming increasingly important sources for knowing people's opinions and sentiments on a wide variety of topics. The huge number of messages published daily in these media makes it impractical to analyze them without the help of natural language processing systems.This article presents an approach to cluster texts by similarity and identifying the sentiments expressed by comments on then (positive, negative and neutral, among others) in an integrated manner. Unlike most of the available studies that focus on the English language and use Twitter as a data source, we treat Brazilian Portuguese posts and comments published on Facebook. The proposed approach employs an unsupervised learning algorithm to group posts and a supervised algorithm to identify the sentiments expressed in comments to posts. In an experimental evaluation, a system that implements the proposed approach showed similar accuracy to that of human evaluators in the tasks of clustering and sentiment analysis, but performed the tasks in much less time.

References

[1] E. Cambria, B. Schuller, Y. Xia, e C. Havasi, “New avenues in opinion mining and sentiment analysis”, IEEE Intell. Syst., no 2, p. 15–21, 2013.

[2] R. Feldman, “Techniques and applications for sentiment analysis”, Commun. ACM, vol. 56, no 4, p. 82–89, 2013.

[3] M. Á. García-Cumbreras, A. Montejo-Ráez, e M. C. Díaz-Galiano, “Pessimists and optimists: Improving collaborative filtering through sentiment analysis”, Expert Syst. Appl., vol. 40, no 17, p. 6758–6765, 2013.

[4] X. Zhang e Y. LeCun, “Text Understanding from Scratch”, Prepr. ArXiv150201710 Cs, fev. 2015.

[5] M. Zhang, Y. Zhang, e D.-T. Vo, “Gated Neural Networks for Targeted Sentiment Analysis”, 2016.

[6] P. Grandin e J. M. Adan, “Piegas: A Systems for Sentiment Analysis of Tweets in Portuguese”, IEEE Lat. Am. Trans., vol. 14, no 7, p. 3467–3473, 2016.

[7] A. Ortigosa, J. M. Martín, e R. M. Carro, “Sentiment analysis in Facebook and its application to e-learning”, Comput. Hum. Behav., vol. 31, p. 527–541, 2014.

[8] S. S. Dasgupta, S. Natarajan, K. K. Kaipa, S. K. Bhattacherjee, e A. Viswanathan, “Sentiment analysis of Facebook data using Hadoop based open source technologies”, in Data Science and Advanced Analytics (DSAA), 2015. 36678 2015. IEEE International Conference on, 2015, p. 1–3.

[9] V. Franzoni, Y. Li, P. Mengoni, e A. Milani, “Clustering Facebook for Biased Context Extraction”, in International Conference on Computational Science and Its Applications, 2017, p. 717–729.

[10] B. Pang, L. Lee, e S. Vaithyanathan, “Thumbs up?: sentiment classification using machine learning techniques”, in Proceedings of the ACL-02 conference on Empirical methods in natural language processing-Volume 10, 2002, p. 79–86.

[11] S. Rosenthal, P. Nakov, S. Kiritchenko, S. M. Mohammad, A. Ritter, e V. Stoyanov, “Semeval-2015 task 10: Sentiment analysis in twitter”, in Proceedings of the 9th International Workshop on Semantic Evaluation, SemEval, 2015.

[12] C. D. Manning, P. Raghavan, e H. Schtze, Introduction to information retrieval. Cambridge University Press New York, NY, USA, 2008.

[13] F. Ceci, A. L. Goncalves, e R. Weber, “A model for sentiment analysis based on ontology and cases”, IEEE Latin America Transactions, vol. 14, nº 11, p. 4560–4566, 2016.

[14] P. O. L. Junior, L. G. de Castro Junior, e A. L. Zambalde, “Applying Textmining to Classify News About Supply and Demand in the Coffee Market”, IEEE Latin America Transactions, vol. 14, nº 12, p. 4768–4774, 2016.

[15] L. P. Del Bosque e S. E. Garza, “Prediction of aggressive comments in social media: an exploratory study”, IEEE Latin America Transactions, vol. 14, nº 7, p. 3474–3480, 2016.

[16] R. G. Rodrigues, R. M. das Dores, C. G. Camilo-Junior, e T. C. Rosa, “SentiHealth-Cancer: a sentiment analysis tool to help detecting mood of patients in online social networks”, International journal of medical informatics, vol. 85, nº 1, p. 80–95, 2016.

[17] B. Ma, H. Yuan, e Y. Wu, “Exploring performance of clustering methods on document sentiment analysis”, Journal of Information Science, vol. 43, nº 1, p. 54–74, 2017.

[18] Y. Wang, K. Kim, B. Lee, e H. Y. Youn, “Word clustering based on POS feature for efficient twitter sentiment analysis”, Human-centric Computing and Information Sciences, vol. 8, nº 1, p. 17, 2018.

[19] M. T. AL-Sharuee, F. Liu, e M. Pratama, “Sentiment analysis: An automatic contextual analysis and ensemble clustering approach and comparison”, Data & Knowledge Engineering, vol. 115, p. 194–213, 2018.

[20] A. R. Afonso e C. G. Duque, “Automated text clustering of newspaper and scientific texts in brazilian portuguese: analysis and comparison of methods”, JISTEM-Journal of Information Systems and Technology Management, vol. 11, nº 2, p. 415–436, 2014.

[21] A. R. Afonso, “Brazilian Portuguese Text Clustering Based on Evolutionary Computing”, IEEE Latin America Transactions, vol. 14, nº 7, p. 3370–3377, 2016.

[22] A. Ceron, L. Curini, e S. M. Iacus, “iSA: a fast, scalable and accurate algorithm for sentiment analysis of social media content”, Inf. Sci., 2016.

[23] N. F. da Silva, E. R. Hruschka, e E. R. Hruschka, “Tweet sentiment analysis with classifier ensembles”, Decis. Support Syst., vol. 66, p. 170–179, 2014.