Elamur Research⌕
☰
home / papers / 2015 / Towards a Contextual Pragmatic Model to Detect Irony in Tweets

Towards a Contextual Pragmatic Model to Detect Irony in Tweets

Summary

The paper addresses automatic irony detection in French tweets. The authors argue that many ironic messages cannot be recognized from their wording alone, because the irony depends on knowledge outside the text. They noticed that most ironic French tweets contain negation. From this they formed two hypotheses: negation helps reveal a gap between literal and intended meaning, and a tweet asserting Not(P) is ironic when external evidence supports P. They collected 6,742 French tweets on media-covered topics from Spring 2014 and split them into negation-only, no-negation and combined corpora. They then trained SMO classifiers in Weka on six groups of features, some established and some new. In a second step, a query-based procedure searches reliable web sources through Google to re-label tweets the classifier wrongly marked as non-ironic. Classification worked best on the combined corpus. The web-query correction gave a small but statistically significant gain on negated tweets. The study describes itself as the earliest research to tackle recognizing ironic content in French-language Twitter data, and as an early step towards using pragmatic context.

Key points

  • Corpus: 6,742 tweets on 184 topics in 9 categories, with irony labels taken from #ironie/#sarcasme hashtags.
    • NegOnly: 470 ironic / 3,761 non-ironic.
    • NoNeg: 1,075 ironic / 1,436 non-ironic.
    • All: 1,545 ironic / 5,197 non-ironic.
    • Negation usage was verified with the Malt parser plus correction rules.
  • Negation is frequent in irony: over 62.75% of sampled ironic French tweets contained explicit negation markers or negative polarity items.
  • Classifiers: three SMO classifiers (C_Neg, C_NoNeg, C_All). C_Neg was evaluated with 10-fold cross-validation on a balanced set of 940 tweets.
    • New features include opposition patterns extending Riloff et al., surprise words, neutral opinions and non-contrastive discourse connectives.
    • The resources used are the CASOAR and EMOTAIX lexicons.
  • Query-based correction: restricted to tweets without personal pronouns and with named entities. On NegOnly, accuracy rose from 74.46 to 74.89 (18 queries, 4 tweets re-labelled as ironic). C_All reached 87.7.
  • Task difficulty: two human annotators agreed only moderately (Cohen's κ = 0.41) on the 50 tweets that received web queries.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Cited by

16 papers of our library cite it (of the 140673 whose bibliographies we read); 7 of them have a page here, 9 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.3115/v1/p15-2106

@inproceedings{karoui2015contextual,
  title = {{Towards a Contextual Pragmatic Model to Detect Irony in Tweets}},
  author = {Karoui, Jihen and Zitoune, Farah Benamara and Moriceau, Véronique and Aussenac-Gilles, Nathalie and Belguith, Lamia Hadrich},
  booktitle = {Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)},
  year = {2015},
  doi = {10.3115/v1/p15-2106},
  url = {https://doi.org/10.3115/v1/p15-2106}
}

References

27 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Salvatore Attardo. 2000. Irony as relevant inappropriateness. Journal of pragmatics, 32(6):793–826. ↗
  2. Francesco Barbieri and Horacio Saggion. 2014. Modelling Irony in Twitter: Feature Analysis and Evaluation. In Proceedings of Language Resources and Evaluation Conference (LREC), pages 4258–4264. find our card
  3. Farah Benamara, Véronique Moriceau, and Yvette Yannick Mathieu. 2014. Fine-grained semantic categorization of opinion expressions for consensus detection (Catégorisation sémantique fine des expressions d’opinion pour la détection de consensus) [in French]. In TALN-RECITAL 2014 Workshop DEFT 2014 : DÉfi Fouille de Textes (DEFT 2014 Workshop: Text Mining Challenge), pages 36–44, July. find
  4. Clint Burfoot and Clint Baldwin. 2009. Automatic satire detection: Are you having a laugh? In Proceedings of the ACL-IJCNLP 2009 conference short papers, pages 161–164. Association for Computational Linguistics. find
  5. Konstantin Buschmeier, Philipp Cimiano, and Roman Klinger. 2014. An Impact Analysis of Features in a Classification Approach to Irony Detection in Product Reviews. In Proceedings of the 5th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, pages 42–49. find our card
  6. Paula Carvalho, Luı́s Sarmento, Mário J Silva, and Eugénio De Oliveira. 2009. Clues for detecting irony in user-generated contents: oh...!! it’s so easy;-). In Proceedings of the 1st international CIKM workshop on Topic-sentiment analysis for mass opinion, pages 53–56. ACM. find
  7. Herbert H Clark and Richard J Gerrig. 1984. On the pretense theory of irony. Journal of Experimental Psychology: General, 113(1):121–126. ↗
  8. Dmitry Davidov, Oren Tsur, and Ari Rappoport. 2010. Semi-supervised Recognition of Sarcastic Sentences in Twitter and Amazon. In Proceedings of the Fourteenth Conference on Computational Natural Language Learning, CoNLL ’10, pages 107–116. find our card
  9. Aniruddha Ghosh, Guofu Li, Tony Veale, Paolo Rosso, Ekaterina Shutova, John Barnden, and Antonio Reyes. 2015. Semeval-2015 task 11: Sentiment Analysis of Figurative Language in Twitter. In Proc. 9th Int. Workshop on Semantic Evaluation (SemEval 2015), Co-located with NAACL, page 470478. Association for Computational Linguistics. find
  10. Raymond W Gibbs. 2000. Irony in talk among friends. Metaphor and symbol, 15(1-2):5–27. ↗
  11. Roberto Gonzalez-Ibanez, Smaranda Muresan, and Nina Wacholde. 2011. Identifying sarcasm in Twitter: a closer look. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: short papers-Volume 2, pages 581–586. Association for Computational Linguistics. find our card
  12. H Paul Grice, Peter Cole, and Jerry L Morgan. 1975. Syntax and semantics. Logic and conversation, 3:41–58. find
  13. Henk Haverkate. 1990. A speech act analysis of irony. Journal of Pragmatics, 14(1):77 – 109. ↗
  14. Christine Liebrecht, Florian Kunneman, and Bosch Antal van den. 2013. The perfect solution for detecting sarcasm in tweets# not. In Proceedings of the 4th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, pages 29–37. New Brunswick, NJ: ACL. find our card
  15. Dan I Moldovan, Sanda M Harabagiu, Roxana Girju, Paul Morarescu, V Finley Lacatusu, Adrian Novischi, Adriana Badulescu, and Orest Bolohan. 2002. LCC Tools for Question Answering. In TREC. find
  16. Antonio Reyes and Paolo Rosso. 2012. Making objective decisions from subjective data: Detecting irony in customer reviews. Decision Support Systems, 53(4):754–760. ↗
  17. Antonio Reyes, Paolo Rosso, and Tony Veale. 2013. A multidimensional approach for detecting irony in twitter. Language resources and evaluation, 47(1):239–268. ↗
  18. Ellen Riloff, Ashequl Qadir, Prafulla Surve, Lalindra De Silva, Nathan Gilbert, and Ruihong Huang. 2013. Sarcasm as Contrast between a Positive Sentiment and Negative Situation. In EMNLP, pages 704–714. find our card
  19. Charlotte Roze, Laurence Danlos, and Philippe Muller. 2012. Lexconn: A French lexicon of discourse connectives. Discours, Multidisciplinary Perspectives on Signalling Text Organisation, 10:(on line). ↗ our card
  20. J. Searle. 1979. Expression and meaning: Studies in the theory of speech acts. Cambridge University. find
  21. Cameron Shelley. 2001. The bicoherence theory of situational irony. Cognitive Science, 25(5):775–818. ↗
  22. Dan Sperber and Deirdre Wilson. 1981. Irony and the use-mention distinction. Radical pragmatics, 49:295–318. find
  23. Oren Tsur, Dmitry Davidov, and Ari Rappoport. 2010. ICWSM-A Great Catchy Name: Semi-Supervised Recognition of Sarcastic Sentences in Online Product Reviews. In ICWSM. find
  24. Akira Utsumi. 1996. A unified theory of irony and its computational formalization. In Proceedings of the 16th conference on Computational linguistics-Volume 2, pages 962–967. Association for Computational Linguistics. find our card
  25. Akira Utsumi. 2004. Stylistic and contextual effects in irony processing. In Proceedings of the 26th Annual Meeting of the Cognitive Science Society, pages 1369–1374. find
  26. Po-Ya Angela Wang. 2013. #Irony or #Sarcasm-A Quantitative and Qualitative Study Based on Twitter. find
  27. Michael Wiegand, Alexandra Balahur, Benjamin Roth, Dietrich Klakow, and Andrés Montoyo. 2010. A Survey on the Role of Negation in Sentiment Analysis. In Proceedings of the Workshop on Negation and Speculation in Natural Language Processing, pages 60–68. Association for Computational Linguistics. find

↑ back to top

This page in Markdown →