Discourse Connectors for Latent Subjectivity in Sentiment Analysis
Rakshit Trivedi, Jacob Eisenstein · 2013
Document-level sentiment analysis can benefit from fine-grained subjectivity, so that sentiment polarity judgments are based on the relevant parts of the document. While finegrained subjectivity annotations are rarely available, encouraging results have been obtained by modeling subjectivity as a latent variable. However, latent variable models fail to capitalize on our linguistic knowledge about discourse structure. We present a new method for injecting linguistic knowledge into latent variable subjectivity modeling, using discourse connectors. Connector-augmented transition features allow the latent variable model to learn the relevance of discourse connectors for subjectivity transitions, without subjectivity annotations. This yields significantly improved performance on documentlevel sentiment analysis in English and Spanish. We also describe a simple heuristic for automatically identifying connectors when no predefined list is available. 1