Ranked WordNet graph for Sentiment Polarity Classification in Twitter

• The purpose of this article is to present a novel approach to Sentiment Polarity Detection in Twitter posts.
• We propose a non-supervised and domain-independent solution to Sentiment Analysis in Twitter.
• The method combines SentiWordNet scores with a random walk analysis of the concepts found in the text over the WordNet graph.
• Several experiments have been performed in order to compare them with other approaches like machine learning solutions.

This paper presents a novel approach to Sentiment Polarity Classification in Twitter posts, by extracting a vector of weighted nodes from the graph of WordNet. These weights are used in SentiWordNet to compute a final estimation of the polarity. Therefore, the method proposes a non-supervised solution that is domain-independent. The evaluation of a generated corpus of tweets shows that this technique is promising.