A Comparison of SVM Versus Naive-Bayes Techniques for Sentiment Analysis in Tweets - A Case Study with the 2013 FIFA Confederations Cup

• André Luiz Firmino Alves UEPB
• Cláudio de Souza Baptista UFCG
• Anderson Almeida Firmino UFCG
• Maxwell Guimarães de Oliveira UFCG
• Anselmo Cardoso de Paiva UFMA

Resumo

The widespread of social communication media on the Web has made available a large volume of opinionated textual data stored in digital format. These media constitute a rich source for sentiment analysis and understanding of the opinions spontaneously expressed. Traditional techniques for sentiment analysis are based on POS Tagger. Considering the Portuguese language, the use of POS Tagging ends up being too costly, due to the complex grammatical structure of this language. Faced with this problem, a case study is carried out in order to compare two techniques for sentiment analysis: a SVM versus Naive-Bayes classifiers. Our study focused on tweets written in Portuguese during the 2013 FIFA Confederations Cup, although our technique could be applied to any other language. The achieved results indicated that the SVM technique surpassed the Naive-Bayes one, concerning performance issues.