Application of Sentiment Analysis Techniques for Text Classification in Virtual Learning Environments

• Mário Silva Ribeiro UFC
• Emanuel Ferreira Coutinho UFC

DOI: https://doi.org/10.5753/ctrle.2020.11407

Abstract

Professors and tutors in a Virtual Learning Environment (VLE) have to deal with large amounts of textual media, which is time consuming and labor intensive. In this scenario, the use of computational tools that assist them in the task of analyzing texts is very attractive. This work proposes the creation of a tool for sentiment analysis in texts of VLE forums. The idea is to identify the general tendency of a class in relation to the subject under discussion, without having to read all the texts, which can be bulky and laborious. An experiment was applied on the SOLAR VLE discussion forums. The results were satisfactory, with an accuracy reaching 79% in the ratings.

Keywords: Sentiment analysis, Virtual Learning Environment, Application

References

Caetano, J. A., Lima, H. S., dos Santos, M. F., e Marquesneto, H. T. (2017). Utilizando análise de sentimentos para definição da homofilia política dos usuários do twitter durante a eleição presidencial americana de 2016. In XXXVII Congresso da Sociedade Brasileira de Computação (CSBC).

Christie, W., Reis, J. C. S., Benevunuto, F., Moro, M. M., e Almeida, V. (2018). Detecção de posicionamento em tweets sobre política no contexto brasileiro. In Brazilian Workshop on Social Network Analysis and Mining (BraSNAM-CSBC).

Coutinho, E. F., Santos, I., e Bezerra, C. I. M. (2017). A software ecosystem for a virtual learning environment: Solar seco. In 2017 IEEE/ACM Joint 5th International Workshop on Software Engineering for Systems-of-Systems and 11th Workshop on Dis-tributed Software Development, Software Ecosystems and Systems-of-Systems (JSOS).

Dosciatti, M. M., Ferreira, L. P. C., e Paraiso, E. C. (2013). Identificando emoções emtextos em português do brasil usando máquina de vetores de suporte em solução multiclasse. In X Encontro Nacional de Inteligência Artificial e Computacional (ENIAC).

Esuli, A. e Sebastiani, F. (2006). Determining term subjectivity and term orientation for opinion mining. In 11th Conference of the European Chapter of the Associationfor Computational Linguistics.

Kansaon, D. P., Brandao, M. A., e de Paula Pinto, S. A. (2018). Análise de sentimentos em tweets em português brasileiro. In Brazilian Workshop on Social Network Analysis and Mining (BraSNAM-CSBC), volume 7.

Liu, B. (2012). Sentiment analysis and opinion mining. Synthesis lectures on human language technologies, 5(1).

O’Leary, R. e Ramsden, A. (2002). Virtual learning environments. In Learning and Teaching Support Network Generic Centre/ALT Guides, LTSN, volume 12.

Oliveira, E., Sales, G., Pereira, P., e Moreira, R. (2013). Identificação automática de estilos de aprendizagem: Uma revisão sistemática da literatura. In Anais do 26o. Workshop sobre Educação em Computação (WEI2018).

Polak, Y. N. S., Diniz, J. A., e Santana, J. R. (2011). Dialogando sobre metodologia científica. Editora Universidade Federal do Ceará.

Sammut, C. and Webb, G. I. (2017). Encyclopedia of Machine Learning. Springer.

Silva, L. (2017). Tweets from mg/br. https://www.kaggle.com/leandrodoze/tweets-from-mgbr. Online; acessado em setembro de 2018.

Tatman, R. (2017). Sentiment lexicons for 81 languages. https://www.kaggle.com/rtatman/sentiment-lexicons-for-81-languagessentiment-lexicons.zip. Online; acessado em setembro de 2018.

Ting, K. M. (2017). Precision and Recall - Encyclopedia of Machine Learning. Springer.

Witten, I. H., Frank, E., e Hall, M. A. (2016). Data Mining: Practical machine learningtools and techniques. Morgan Kaufmann.