CatSent: a Catalan sentiment analysis website

Abstract

In this paper we investigate, analyze and compare sentimental analysis methodologies in Catalan tweets. The main goal is to develop a high-performance Catalan classifier. There are three main steps: Catalan language preprocessing tool, classification model and corpus training. The preprocessing tool is used for cleaning and extracting features from a document (or tweet). This is a key step due to the great morphological complexity of the Catalan language. The tool will remove empty words from the text and find the roots of other words. The classification algorithm will divide the tweet into “positive” and “negative” classes. To choose the best algorithm, five models are compared: Naive Bayes, Maximum Entropy, Support Vector Machine, Decision Tree and Neural Networks. Finally, the corpus will be used for training and testing these methods. There is no known public corpus in Catalan, so we created one using a lexicon-based approach. This work aims to enable the tools to carry out sentiment analysis studies in the Catalan language. The last step is to develop a public web service with the best classification model achieved where users will be able to check its effectiveness.