ABSTRACT:
Sentiment analysis concerns the computational study of opinions expressed in text. Social media domains provide a wealth of opinionated data, thus, creating a greater need for sentiment analysis. Typically, sentiment lexicons that capture term-sentiment association knowledge are commonly used to develop sentiment analysis systems. Given that sentiment scores are associated to word senses in SentiWordNet, it is imperative to investigate the applicability of word sense disambiguation (WSD) in determining the correct sense for terms in relation to other score extraction approaches that avoid word sense disambiguation. To this end, we formalise score extraction approaches from the existing literature and introduce a Lesk-like algorithm for WSD. The results confirm that word sense disambiguation is useful on social media domains that have relatively longer documents (e.g. discussion posts).
Keywords:
Sentiment analysis, Sentiment lexicons, Score extraction, Word sense disambiguation
