The DsUniPi team participated in the SemEval 2015 Task#11: Sentiment Analysis of Figurative Language in Twitter. The proposed approach employs syntactical and morphological features, which indicate sentiment polarity in both figurative and non-figurative tweets. These features were combined with others that indicate presence of figurative language in order to predict a fine-grained sentiment score. The method is supervised and makes use of structured knowledge resources, such as Senti-WordNet sentiment lexicon for assigning sentiment score to words and WordNet for calculating word similarity. We have experimented with different classification algorithms (Naieve Bayes, Decision trees, and SVM), and the best results were achieved by an SVM classifier with linear kernel.
展开▼
