Sentiment Analysis of Figurative Language using a Word Sense Disambiguation Approach
Vassiliki Rentoumi, George Giannakopoulos, Vangelis Karkaletsis and George Vouros
In: RANLP 2009, 14-16 Sep 2009, Borovets, Bulgaria.
In this paper we propose a methodology for sentiment analysis of ﬁgurative language which applies Word Sense Disambiguation and, through
an n-gram graph based method, assigns polarity to word senses. Polarity assigned to senses, combined with contextual valence shifters, is exploited for further assigning polarity to sentences, using Hidden Markov Models. Evaluation results using the corpus of the Aﬀective Text
task of SemEval’07, are presented together with a comparison with other state-of-the-art methods, showing that the proposed method provides promising results, and positive evidence supporting our conjecture: ﬁgurative language conveys sentiment.