Semi-Supervised Recognition of Sarcasm in Twitter and Amazon

Sarcasm is a form of speech act in which the speakers convey their message in an implicit way. The inherently ambiguous nature of sarcasm sometimes makes it hard even for humans to decide whether an utterance is sarcastic or not. Recognition of sarcasm can benefit many sentiment analysis NLP applications, such as review summarization, dialogue systems and review ranking systems. In this paper we experiment with semisupervised sarcasm identification on two very different data sets: a collection of 5.9 million tweets collected from Twitter, and a collection of 66000 product reviews from Amazon. Using the Mechanical Turk we created a gold standard sample in which each sentence was tagged by 3 annotators, obtaining F-scores of 0.78 on the product reviews dataset and 0.83 on the Twitter dataset. We discuss the differences between the datasets and how the algorithm uses them (e.g., for the Amazon dataset the algorithm makes use of structured information). We also discuss the utility of Twitter #sarcasm hashtags for the task.