Improving Subjectivity Detection using Unsupervised Subjectivity Word Sense Disambiguation

Resumen

In this work, we present a sentence-level subjectivity detection method, which relies on Subjectivity Word Sense Disambiguation (SWSD). We use an unsupervised sense clustering-based method for SWSD. In our method, semantic resources tagged with emotions and sentiment polarities are used to apply subjectivity detection, intervening Word Sense Disambiguation sub-tasks. Through an experimental study, we empirically validated the proposed method over two subjectivity collections, MPQA Corpus and Movie Review Dataset, using three widely popular opinion-mining resources SentiWordNet, WordNet-Affect and Micro-WNOp. The results show that our proposal performs significantly better than our proposed baseline.