Análise dos sentimentos expressos na rede social Twitter em relação aos filmes indicados ao Oscar 2017

Abstract

Social networks are places on the Internet that allow the creation and sharing of content, being important sources of information and opinions. The film industry benefits from social networks, because they can be used to promote movies and as sources of opinions that may influence forthcoming releases and the way they are promoted to the public. This paper aims to perform the sentiment analysis of Twitter posts related to the movies nominated for Best Picture of the 2017 Oscars. Data from this network were collected and then the steps of a Sentiment Analysis task were performed. Several text classifiers were studied and applied to a labeled database and, after assessing them, the multinomial Naive Bayes classifier was chosen to classify the complete database. It was noticed that this method is interesting to make observations and analyses about this database, once it was able to predict which movie would be the winner of the cerimony and which would be among the less prestigious ones. However, no significant mathematical correlations were found between the result of the 2017 Oscars and the results obtained from the analysis of tweets' sentiments. It has also been noted that Twitter users prefer to use the network to post positive comments about movies rather than saying bad things about the ones they did not like. Furthermore, it was found that award shows such as the Oscars cause a growth on the number of posts on Twitter.