An Ensemble of Humour, Sarcasm, and Hate Speechfor Sentiment Classification in Online Reviews

AbstractDue to the nature of online user reviews, sentiment analysis on such data requires a deep semantic understanding of the text. Many online reviews are sarcastic, humorous, or hateful. Signals from such language nuances may reinforce or completely alter the sentiment of a review as predicted by a machine learning model that attempts to detect sentiment alone. Thus, having a model that is explicitly aware of these features should help it perform better on reviews that are characterized by them. We propose a composite two-step model that extracts features pertaining to sarcasm, humour, hate speech, as well as sentiment, in the first step, feeding them in conjunction to inform sentiment classification in the second step. We show that this multi-step approach leads to a better empirical performance for sentiment classification than a model that predicts sentiment alone. A qualitative analysis reveals that the conjunctive approach can better capture the nuances of sentiment as expressed in online reviews.