Sentiment Analysis Through Finite State Automata

The present research aims to demonstrate how powerful Finite State Automata (FSA) can be, into a domain in which the vagueness of the human opinions and the subjectivity of the user generated contents make the automatic “understanding” of texts extremely hard. Assuming that the semantic orientation of sentences is based on the manipulation of sentiment words, we built from scratch, for the Italian language, a network of local grammars for the annotation of sentiment expressions and electronic dictionaries for the classification of more than 15,000 opinionated words. In the paper we explain in detail how we made use of FSA for both the automatic population of sentiment lexicons and the sentiment classification of real sentences.