Lexical Influences on the Perception of Sarcasm
Summary
Sarcasm is usually seen as a pragmatic phenomenon that depends on context and on knowledge shared between speakers. This view has led some to doubt that software could ever recognize it. Kreuz and Caucci test whether word-level cues also shape how readers judge sarcastic intent. Instead of invented stimuli, they used real narrative passages from Google Book Search. They took 100 excerpts where an author had written "said sarcastically" and removed the adverb. They added 15 control excerpts containing a plain "I/he/she said." Undergraduates rated how likely each highlighted utterance was to be sarcastic. Two judges coded each utterance for adjectives or adverbs, interjections, and exclamation or question marks. Readers reliably told the originally sarcastic passages apart from the controls. A regression controlled for excerpt length, and only interjections such as gee or gosh significantly predicted the ratings, explaining about 5% of the variance. The authors conclude that sarcasm is partly formulaic. Simple lexical cues could therefore help NLP systems flag non-literal language without fully modeling pragmatics.
Key points
- Data: 115 excerpts from Google Book Search (100 sarcastic, 15 control) with a mean length of 110 words. The highlighted target utterances averaged 6.45 words.
- Participants: 101 undergraduates took part. Each rated 20 sarcastic excerpts, drawn from one of five sets, plus all 15 controls on a 7-point likelihood scale.
- Rating difference: Sarcastic excerpts were rated higher (M = 4.85) than controls (M = 2.89), with t(100) = 19.35 and p < .001.
- Regression results: Inter-judge coding agreement was 95%. Excerpt length was not significant (R² = .024). Interjections were significant (F(1,111) = 6.10, p = .015, R² = .051). Adjectives/adverbs and punctuation were not significant predictors.
- Qualitative observations: Sarcastic utterances often contained set phrases, foreign expressions, rhetorical remarks, and repetitions, though the sample was too small to analyze these. Some authors used "sarcastically" loosely to mean angrily or jokingly.
Cited by
- An Impact Analysis of Features in a Classification Approach to Irony Detection in Product Reviews
- Irony and Sarcasm: Corpus Generation and Analysis Using Crowdsourcing
- Fracking Sarcasm using Neural Network
- CASCADE: Contextual Sarcasm Detection in Online Discussion Forums
- Identifying Sarcasm in Twitter: A Closer Look
- C-Net: Contextual Network for Sarcasm Detection
- Are Word Embedding-based Features Useful for Sarcasm Detection?
- Automatic Sarcasm Detection: A Survey
- Harnessing Sequence Labeling for Sarcasm Detection in Dialogue from TV Series ‘Friends'
- How Challenging is Sarcasm versus Irony Classification?: A Study With a Dataset from English Literature
- Representing Social Media Users for Sarcasm Detection
- When did you become so smart, oh wise one?! Sarcasm Explanation in Multi-modal Multi-party Dialogues
- Sarcasm as Contrast between a Positive Sentiment and Negative Situation
- NLPRL-IITBHU at SemEval-2018 Task 3: Combining Linguistic Features and Emoji pre-trained CNN for Irony Detection in Tweets
- Tweet Sarcasm Detection Using Deep Neural Network
Cite
@inproceedings{kreuz2007lexical,
title = {{Lexical Influences on the Perception of Sarcasm}},
author = {Kreuz, Roger and Caucci, Gina},
booktitle = {Proceedings of the Workshop on Computational Approaches to Figurative Language},
year = {2007},
doi = {10.3115/1611528.1611529},
url = {https://doi.org/10.3115/1611528.1611529}
}References
- Herbert H. Clark, 1996. Using Language. Cambridge: Cambridge University Press. find
- Shelly Dews and Ellen Winner, 1997. Attributing meaning to deliberately false utterances: The case of irony. In C. Mandell and A. McCabe (Eds.), The Problem of Meaning: Behavioral and Cognitive Perspectives. Amsterdam: Elsevier. find
- Raymond W. Gibbs, Jr., 1994. The Poetics of Mind: Figurative Thought, Language, and Understanding. Cambridge: Cambridge University Press. find
- Raymond W. Gibbs, Jr., 2003. Nonliteral speech acts in text and discourse. In A. C. Graesser, M. A. Gernsbacher, and S. R. Goldman (Eds.), Handbook of Discourse Processes (pp. 357-393). Mahwah, NJ: Lawrence Erlbaum Associates. ↗
- Rachel Giora, 2003. On our Mind: Salience, Context, and Figurative Language. New York: Oxford University Press. find
- Roger J. Kreuz, 1996. The use of verbal irony: Cues and constraints. In J. S. Mio and A. N. Katz (Eds.), Metaphor: Implications and Applications (pp. 23-38). Mahwah, NJ: Lawrence Erlbaum Associates Roger J. Kreuz, Megan L. Dress, and Kristen E. Link, 2006, July. Regional Differences in the Spontaneous Use of Sarcasm. Paper presented at the annual meeting of the Society for Text and Discourse, Minneapolis, MN. find
- Roger J. Kreuz and Sam Glucksberg, 1989. How to be sarcastic: The echoic reminder theory of verbal irony. Journal of Experimental Psychology: General, 118:374-386. ↗
- Roger J. Kreuz, Max A. Kassler, Lori Coppenrath, and Bonnie McLain Allen, 1999. Tag questions and common ground effects in the perception of verbal irony. Journal of Pragmatics, 31:1685-1700. ↗
- Roger J. Kreuz and Kristen E. Link, 2002. Asymmetries in the use of verbal irony. Journal of Language and Social Psychology, 21:127-143. ↗
- Roger J. Kreuz and Richard M. Roberts, 1995. Two cues for verbal irony: Hyperbole and the ironic tone of voice. Metaphor and Symbolic Activity, 10:21-31. ↗
- Geoffrey Nunberg, 2001. The Way we Talk Now: Commentaries on Language and Culture. Boston: Houghton Mifflin Akira Utsumi, 2000. Verbal irony as implicit display of ironic environment: Distinguishing ironic utterances from nonirony. Journal of Pragmatics, 32:1777-1806. find