Putting Sarcasm Detection into Context: The Effects of Class Imbalance and Manual Labelling on Supervised Machine Classification of Twitter Conversations

Sarcasm can radically alter or invert a phrase’s meaning. Sarcasm detection can therefore help improve natural language processing (NLP) tasks. The majority of prior research has modeled sarcasm detection as classification, with two important limitations: 1. Balanced datasets, when sarcasm is actually rather rare. 2. Using Twitter users’ self-declarations in the form of hashtags to label data, when sarcasm can take many forms. To address these issues, we create an unbalanced corpus of manually annotated Twitter conversations. We compare human and machine ability to recognize sarcasm on this data under varying amounts of context. Our results indicate that both class imbalance and labelling method affect performance, and should both be considered when designing automatic sarcasm detection systems. We conclude that for progress to be made in real-world sarcasm detection, we will require a new class labelling scheme that is able to access the ‘common ground’ held between conversational parties.