An approach to improve the accuracy of probabilistic classifiers for decision support systems in sentiment analysis

Abstract

Social networks link people and machines, providing a huge amount of information that grows very fast without the possibility to be handled manually. Moreover, opinion mining is the process of using natural language processing, text analytics and computational linguistics to identify and extract subjective information in different sources such as social networks. To that, classification methods are used but due to the limitless number of topics and the breadth and ambiguity of natural language, with its peculiarities in social networks, the results can be greatly improved. In this work, we present DSociaL, a platform to automate the processing of information obtained from social networks, focusing on improving the accuracy of decision support systems for sentiment analysis. We focus on machine learning-based simple probabilistic classifiers, evaluating a naive Bayes classifier, the basis of one of the most used soft computing techniques. Thus, we show a use case in which the proposal, with definitions and refinements made by experts, helps to improve the prediction of users’ feelings towards a movie compared to what would happen with a conventional approach.