Elamur Research⌕
☰
home / papers / 2011 / Mining Subjective Knowledge from Customer Reviews: A Specific Case of Irony Detection

Mining Subjective Knowledge from Customer Reviews: A Specific Case of Irony Detection

Summary

Reyes and Rosso address irony as a source of error in sentiment analysis, because ironic text often says the opposite of what it means. They take a broad view of irony that also covers sarcasm, satire and humor. Instead of annotating data by hand, they build a corpus from Amazon reviews that went viral and were widely recognised as ironic. They keep only reviews rated four stars or higher, reasoning that mock praise gets top ratings. These are set against ordinary Amazon reviews (AMA) and comments tagged as funny on Slashdot (SLA). The authors then propose a model with six feature categories: word n-grams, POS n-grams, and profiles for funniness, positive/negative polarity, affect and pleasantness. They test it with three classifiers. The authors describe accuracy, precision, recall and F-measure as satisfactory. Information-gain analysis shows that the most useful features depend on which negative set is used. The work matters because it releases a free irony data set. It also offers evidence that irony relies on positive wording to convey negative meaning.

Key points

  • Ironic set: 3,163 reviews were collected for five viral Amazon products, including the Three Wolf Moon T-shirt, Tuscan Whole Milk and Uranium Ore. Removing reviews rated below four stars left 2,861 ironic documents.
  • Negative sets and access: AMA and SLA contain 3,000 documents each, giving a corpus of 8,861 documents. It is freely available from the UPV NLE group site.
  • Text features: Word n-grams of order 2 to 7 were extracted after stopword removal, stemming and tf-idf filtering, with 824 terms filtered out. POS-grams capture abstract morphosyntactic templates.
  • Most informative features by information gain:
    • For AMA: POS 3-grams, pleasantness and funny.
    • For SLA: pleasantness, word 5-grams and funny.
  • Lexicon-based findings:
    • Ironic texts are dominated by positive words, even though the negative list in the MSOL lexicon is much larger.
    • Pleasantness noticeably improved accuracy.
    • Affective features proved less important than the authors had expected.

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

8 papers of our library cite it (of the 140673 whose bibliographies we read); 2 of them have a page here, 6 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work.

@inproceedings{reyes2011mining,
  title = {{Mining Subjective Knowledge from Customer Reviews: A Specific Case of Irony Detection}},
  author = {Reyes, Antonio and Rosso, Paolo},
  booktitle = {Proceedings of the 2nd Workshop on Computational Approaches to Subjectivity and Sentiment Analysis (WASSA 2.011)},
  year = {2011},
  url = {https://aclanthology.org/W11-1715/}
}

References

27 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. J. Atserias, B. Casas, E. Comelles, M. González, L. Padró, and M Padró. 2006. Freeling 1.3: Syntactic and semantic services in an open-source nlp library. In Proceedings of the 5th International Conference on Language Resources and Evaluation, pages 48–55. find
  2. S. Attardo. 2007. Irony as relevant inappropriateness. In R. Gibbs and H. Colston, editors, Irony in Language and Thought, pages 135–174. Taylor and Francis Group. find
  3. L. Bentivogli, P. Forner, B. Magnini, and E. Pianta. 2004. Revising the wordnet domains hierarchy: semantics, coverage and balancing. In Gilles Sérasset, editor, Multilingual Linguistic Resources, pages 94–101. find
  4. T. Brants and A. Franz. 2006. Web 1t 5-gram corpus version 1. find
  5. C. Burfoot and T. Baldwin. 2009. Automatic satire detection: Are you having a laugh? In ACL-IJCNLP ’09: Proceedings of the ACL-IJCNLP 2009 Conference Short Papers, pages 161–164. find
  6. P. Carvalho, L. Sarmento, M. Silva, and E. de Oliveira. 2009. Clues for detecting irony in user-generated contents: oh...!! it’s “so easy” ;-). In TSA ’09: Proceeding of the 1st international CIKM workshop on Topic-sentiment analysis for mass opinion, pages 53–56. find
  7. H. Colston and R. Gibbs. 2007. A brief history of irony. In R. Gibbs and H. Colston, editors, Irony in Language and Thought, pages 3–24. Taylor and Francis Group. find
  8. H. Colston. 2007. On necessary conditions for verbal irony comprehension. In R. Gibbs and H. Colston, editors, Irony in Language and Thought, pages 97–134. Taylor and Francis Group. find
  9. I. Councill, R. McDonald, and L. Velikovich. 2010. What’s great and what’s not: learning to classify the scope of negation for improved sentiment analysis. In Proceedings of the Workshop on Negation and Speculation in Natural Language Processing, pages 51–59, July. find
  10. C. Curcó. 2007. Irony: Negation, echo, and metarepresentation. In R. Gibbs and H. Colston, editors, Irony in Language and Thought, pages 269–296. Taylor and Francis Group. find
  11. D. Davidov, O. Tsur, and A. Rappoport. 2010. Semi-supervised recognition of sarcastic sentences in Twitter and Amazon. In Proceeding of the 23rd international conference on Computational Linguistics, July. find our card
  12. R. Gibbs and H. Colston. 2007. The future of irony studies. In R. Gibbs and H. Colston, editors, Irony in Language and Thought, pages 339–360. Taylor and Francis Group. find
  13. R. Gibbs. 2007. Irony in talk among friends. In R. Gibbs and H. Colston, editors, Irony in Language and Thought, pages 339–360. Taylor and Francis Group. 124 find
  14. R. Giora. 1995. On irony and negation. Discourse Processes, 19(2):239–264. ↗
  15. H. Grice. 1975. Logic and conversation. In Peter Cole and Jerry L. Morgan, editors, Syntax and semantics, volume 3, pages 41–58. New York: Academic Press. ↗
  16. X. Lü, L. Zhang, and J. Hu. 2004. Statistical substring reduction in linear time. In Proceedings of IJCNLP-04, HaiNan island. find
  17. J. Lucariello. 2007. Situational irony: A concept of events gone away. In R. Gibbs and H. Colston, editors, Irony in Language and Thought, pages 467–498. Taylor and Francis Group. find
  18. R. Mihalcea and C. Strapparava. 2006. Learning to Laugh (Automatically): Computational Models for Humor Recognition. Journal of Computational Intelligence, 22(2):126–142. ↗
  19. G. Miller. 1995. Wordnet: A lexical database for english. Communications of the ACM, 38(11):39–41. find our card
  20. A. Reyes, P. Rosso, and D. Buscaldi. 2009. Humor in the blogosphere: First clues for a verbal humor taxonomy. Journal of Intelligent Systems, 18(4):311–331. ↗
  21. M. Saif, D. Cody, and D. Bonnie. 2009. Generating high-coverage semantic orientation lexicons from overtly marked words and a thesaurus. In Proceedings of the 2009 Conference on EMNLP, pages 599–608, Morristown, NJ, USA. Association for Computational Linguistics. find
  22. C. Strapparava and A. Valitutti. 2004. WordNet-affect: an affective extension of WordNet. In Proceedings of the 4th International Conference on Language Resources and Evaluation, volume 4, pages 1083–1086. find our card
  23. O. Tsur, D. Davidov, and A. Rappoport. 2010. {ICWSM} — a great catchy name: Semi-supervised recognition of sarcastic sentences in online product reviews. In William W. Cohen and Samuel Gosling, editors, Proceedings of the Fourth International AAAI Conference on Weblogs and Social Media, pages 162– 169, Washington, D.C., 23-26 May. The AAAI Press. find
  24. A. Utsumi. 1996. A unified theory of irony and its computational formalization. In Proceedings of the 16th conference on Computational Linguistics, pages 962– 967, Morristown, NJ, USA. Association for Computational Linguistics. find our card
  25. T. Veale and Y. Hao. 2009. Support structures for linguistic creativity: A computational analysis of creative irony in similes. In Proceedings of CogSci 2009, the 31st Annual Meeting of the Cognitive Science Society, pages 1376–1381. find
  26. C. Whissell. 1989. The dictionary of affect in language. Emotion: Theory, Research, and Experience, 4:113– 131. ↗
  27. D. Wilson and D. Sperber. 2007. On verbal irony. In R. Gibbs and H. Colston, editors, Irony in Language and Thought, pages 35–56. Taylor and Francis Group. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/papers/reyes-2011-mining-subjective-knowledge-customer-reviews/