Temporal Analysis of Sentiment in Tweets: A Case Study with FIFA Confederations Cup in Brazil

摘要

The widespread of social communication media over the Web has made available a large volume of opinionated textual data. These media constitute a rich source for sentiment analysis and understanding of the opinions spontaneously expressed. The traditional techniques for sentiment analysis are based on POS Tagger and its usage ends up being too costly when considering the Portuguese language, due to the complex grammatical structure of this language. Faced with such problem, this paper presents a case study carried out in order to evaluate a technique developed for sentiment analysis based on Bayesian Classifiers. Although our technique could be applied to any language, the present study focused on tweets posted in Portuguese during the 2013 FIFA Confederations Cup. The achieved results represent one of the best applied to the Portuguese language.