Magnets for Sarcasm: Making Sarcasm Detection Timely, Contextual and Very Personal

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 482–491 Copenhagen, Denmark, September 7–11, 2017. c⃝2017 Association for Computational Linguistics Magnets for Sarcasm: Making Sarcasm Detection Timely, Contextual and Very Personal Aniruddha Ghosh University College Dublin, Ireland. Aniruddha.Ghosh@ucdconnect.ie Tony Veale University College Dublin, Ireland. Tony.Veale@ucd.ie Abstract Sarcasm is a pervasive phenomenon in so- cial media, permitting the concise commu- nication of meaning, affect and attitude. Concision requires wit to produce and wit to understand, which demands from each party knowledge of norms, context and a speaker’s mindset. Insight into a speaker’s psychological profile at the time of pro- duction is a valuable source of context for sarcasm detection. Using a neural archi- tecture, we show significant gains in de- tection accuracy when knowledge of the speaker’s mood at the time of production can be inferred. Our focus is on sarcasm detection on Twitter, and show that the mood exhibited by a speaker over tweets leading up to a new post is as useful a cue for sarcasm as the topical context of the post itself. The work opens the door to an empirical exploration not just of sarcasm in text but of the sarcastic state of mind. 1 Introduction Oscar Wilde memorably described sarcasm as “the lowest form of wit but the highest form of intelli- gence.” Though sarcasm lacks the sophistication of irony, and does little to conceal the speaker’s disdain for a target, it is a figurative device that re- quires as much intelligence from its consumers as its producers. The concision with which sarcasm and irony allow speakers to conflate propositional content and affective stance makes it a perva- sive mode of communication in the 140-character tweets of Twitter. By combining an overtly posi- tive attitude with a meaning that is more deserv- ing of scorn, sarcasm allows speakers to commu- nicate disappointment about a state of affairs that bites (or etymologically “cuts the flesh”) of an ad- dressee. It conveys the feeling the speaker would wish to experience (“I love it when ...”) with the state of affairs that up-ends this feeling (“... my friends forget my birthday”). It often combines politeness with mockery to disguise the appear- ance of hostility while heightening its effect on a listener (Brown and Levinson, 1978; Dews and Winner, 1995). It establishes a wry environment (Dews and Winner, 1999) that has its roots in so- cial norms and the speaker’s state of mind. Psychological theories of irony, such as echoic reminder theory (Kreuz and Glucksberg, 1989) and implicit display theory (Utsumi, 2000b) have yet to fully translate into text-analytic methods. Neuropsychology researchers who have sought patterns of brain activity to identify the neural cor- relates of sarcasm note that an understanding of sarcasm is highly dependent not just on the con- text of an utterance but on the state-of-mind and personality of the speaker, as well as on facial expressions and prosody (Shamay-Tsoory et al., 2005). Without the latter markers, purely textual detection must depend largely …

Content truncated to 500 words