NILC_USP: A Hybrid System for Sentiment Analysis in Twitter Messages
Pedro Balage Filho, Thiago Alexandre Salgueiro Pardo · 2013
This paper describes the NILC USP system that participated in SemEval-2013 Task 2: Sentiment Analysis in Twitter. Our system adopts a hybrid classification process that uses three classification approaches: rulebased, lexicon-based and machine learning approaches. We suggest a pipeline architecture that extracts the best characteristics from each classifier. Our system achieved an F-score of 56.31 % in the Twitter message-level subtask. 1