A Study on Classification Methods Applied to Sentiment Analysis

Sentiment analysis is a new area of research in data mining that concerns the detection of opinions and/or sentiments in texts. This work focuses on the application and the comparison of three classification techniques over a text corpus composed of reviews of commercial products in order to detect opinions about them. The chosen domain is about "perfumes", and user opinions composing the corpus are written in Italian language. The proposed approach is completely data-driven: a Term Frequency / Inverse Document Frequency (TFIDF) terms selection procedure has been applied in order to make computation more efficient, to improve the classification results and to manage some issues related to the specific classification procedure adopted.