Elamur Research⌕
☰
home / papers / 2013 / Relational Features in Fine-Grained Opinion Analysis

Relational Features in Fine-Grained Opinion Analysis

Paper · 2013 · Richard Johansson and Alessandro Moschitti

Summary

Most systems for fine-grained opinion analysis treat each opinion expression in a sentence on its own and ignore how opinions relate to each other. Johansson and Moschitti test whether modeling these interactions helps three tasks on the MPQA corpus: marking opinion expressions, linking them to their holders, and assigning polarity. They design relational features that connect pairs of opinion expressions, mostly through dependency-syntactic and semantic role structures, and these links can span any distance in the sentence. Because the features look at several expressions at once, exact search becomes intractable. The authors therefore use reranking. A baseline sequence labeler with local features proposes a k-best list, and a discriminative reranker with the relational features picks the final analysis. They compare several learning methods and feature sets for the reranker. The approach clearly beats both their baselines and earlier published systems. The extracted MPQA-style expressions also add useful features to two practical review-mining applications. The work shows that the structure linking opinions within a sentence is a valuable signal.

Key points

  • On opinion expression extraction, the best reranker improves soft recall by about 10 points and F-measure by about 5 points over a local-feature sequence labeler, with only a small loss in precision. It also beats earlier tools by 6 points of overlap F-measure.
  • Modeling interactions improves recall by almost 10 points for holder extraction (more than 3 F-measure points) and by 7 points for polarity-labeled extraction (about 4 F-measure points). The polarity-labeled results are 10–15 F-measure points above the best previous end-to-end system.
  • Models using both syntactic and semantic structure perform best. The most useful features are purely structural tree fragments, while word-based features matter less.
  • In extrinsic tests, features derived from opinion expressions significantly improve both extraction of product-attribute evaluations and document polarity classification of reviews. These gains hold even against strong sentiment-lexicon baselines and across several review domains, although MPQA consists mostly of political news.

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

 Institutions

🎓University of TrentoTrento · Italy85 works · 15,524 citations🎓University of GothenburgGothenburg · Sweden34 works · 1,625 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

Cite

Cite as Richard Johansson and Alessandro Moschitti. 2013. Relational Features in Fine-Grained Opinion Analysis. Computational Linguistics.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.1162/coli_a_00141

@article{johansson2013relational,
  title = {{Relational Features in Fine-Grained Opinion Analysis}},
  author = {Richard Johansson and Alessandro Moschitti},
  journal = {Computational Linguistics},
  year = {2013},
  doi = {10.1162/coli\_a\_00141},
  url = {https://doi.org/10.1162/coli_a_00141}
}

References

57 references, 24 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Asher, Nicholas, Farah Benamara, and Yannick Mathieu. 2009. Appraisal of opinion expressions in discourse. Lingvisticae Investigations, 31(2):279–292. find
  2. Bethard, Steven, Hong Yu, Ashley Thornton, Vasileios Hatzivassiloglou, and Dan Jurafsky. 2005. Extracting opinion propositions and opinion holders using syntactic and lexical cues. In James G. Shanahan, Yan Qu, and Janyce Wiebe, editors, Computing Attitude and Affect in Text: Theory and Applications… find
  3. Blitzer, John, Mark Dredze, and Fernando Pereira. 2007. Biographies, Bollywood, boom-boxes and blenders: Domain adaptation for sentiment classification. In Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics (ACL-07), pages 440–447, Prague.
  4. Boser, Bernhard, Isabelle Guyon, and Vladimir Vapnik. 1992. A training algorithm for optimal margin classifiers. In Proceedings of the Fifth Annual Workshop on Computational Learning Theory, pages 144–152, Pittsburgh, PA. find
  5. Breck, Eric, Yejin Choi, and Claire Cardie. 2007. Identifying expressions of opinion in context. In IJCAI 2007, Proceedings of the 20th International Joint Conference on Artificial Intelligence, pages 2,683–2,688, Hyderabad. find
  6. Choi, Yejin, Eric Breck, and Claire Cardie. 2006. Joint extraction of entities and relations for opinion recognition. In Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing, pages 431–439, Sydney. find
  7. Choi, Yejin and Claire Cardie. 2008. Learning with compositional semantics as structural inference for subsentential sentiment analysis. In Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pages 793–801, Honolulu, HI.
  8. Choi, Yejin and Claire Cardie. 2010. Hierarchical sequential learning for extracting opinions and their attributes. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pages 269–274, Uppsala. find
  9. Collins, Michael. 2000. Discriminative reranking for natural language parsing. In Proceedings of the Seventeenth International Conference on Machine Learning, pages 175–182, San Francisco, CA.
  10. Collins, Michael. 2002. Discriminative training methods for hidden Markov models: Theory and experiments with perceptron algorithms. In Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing (EMNLP 2002), pages 1–8, Philadelphia, PA.
  11. Crammer, Koby, Ofer Dekel, Joseph Keshet, Shai Shalev-Schwartz, and Yoram Singer. 2006. Online passive-aggressive algorithms. Journal of Machine Learning Research, 2006(7):551–585. find
  12. Crammer, Koby and Yoram Singer. 2001. On the algorithmic implementation of multiclass kernel-based vector machines. Journal of Machine Learning Research, 2001(2):265–585. find
  13. Fan, Rong-En, Kai-Wei Chang, Cho-Jui Hsieh, Xiang-Rui Wang, and Chih-Jen Lin. 2008. L IBLINEAR : A library for large linear classification. Journal of Machine Learning Research, 9:1871–1874. find
  14. Freund, Yoav and Robert E. Schapire. 1999. Large margin classification using the perceptron algorithm. Machine Learning, 37(3):277–296. find
  15. Gerber, Matthew and Joyce Chai. 2010. Beyond NomBank: A study of implicit arguments for nominal predicates. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pages 1,583–1,592, Uppsala.
  16. Greene, Stephan and Philip Resnik. 2009. More than words: Syntactic packaging and implicit sentiment. In Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pages 503–511, Boulder, CO.
  17. Hjorth, J. S. Urban. 1993. Computer Intensive Statistical Methods. Chapman and Hall, London. find
  18. Hu, Minqing and Bing Liu. 2004a. Mining and summarizing customer reviews. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-04), pages 168–177, Seattle, WA. find
  19. Hu, Minqing and Bing Liu. 2004b. Mining opinion features in customer reviews. In Proceedings of the Nineteeth National Conference on Artificial Intellgience (AAAI-2004), pages 755–760, San Jose, CA. find
  20. Huang, Liang. 2008. Forest reranking: Discriminative parsing with non-local features. In Proceedings of ACL-08: HLT, pages 586–594, Columbus, OH. find
  21. Jijkoun, Valentin, Maarten de Rijke, and Wouter Weerkamp. 2010. Generating focused topic-specific sentiment lexicons. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pages 585–594, Uppsala. find
  22. Joachims, Thorsten. 2002. Learning to Classify Text using Support Vector Machines. Kluwer/Springer, Boston. find
  23. Joachims, Thorsten, Thomas Finley, and Chun-Nam Yu. 2009. Cutting-plane training of structural SVMs. Machine Learning, 77(1):27–59. find
  24. Johansson, Richard and Pierre Nugues. 2008. Dependency-based syntactic–semantic analysis with PropBank and NomBank. In CoNLL 2008: Proceedings of the Twelfth Conference on Natural Language Learning, pages 183–187, Manchester. find
  25. Joshi, Mahesh and Carolyn Penstein-Rosé. 2009. Generalizing dependency features for opinion mining. In Proceedings of the ACL-IJCNLP 2009 Conference Short Papers, pages 313–316, Singapore. find
  26. Karlgren, Jussi, Gunnar Eriksson, Magnus Sahlgren, and Oscar Täckström. 2010. Between bags and trees—Constructional patterns in text used for attitude identification. In Proceedings of ECIR 2010, 32nd European Conference on Information Retrieval, pages 38–49, Milton Keynes. find
  27. Kim, Soo-Min and Eduard Hovy. 2006. Extracting opinions, opinion holders, and topics expressed in online news media text. In Proceedings of the Workshop on Sentiment and Subjectivity in Text, pages 1–8, Sydney.
  28. Kobayashi, Nozomi, Kentaro Inui, and Yuji Matsumoto. 2007. Extracting aspect-evaluation and aspect-of relations in opinion mining. In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pages 1,065–1,… find
  29. Mel’čuk, Igor A. 1988. Dependency Syntax: Theory and Practice. State University Press of New York, Albany. find
  30. Meyers, Adam, Ruth Reeves, Catherine Macleod, Rachel Szekely, Veronika Zielinska, Brian Young, and Ralph Grishman. 2004. The NomBank project: An interim report. In HLT-NAACL 2004 Workshop: Frontiers in Corpus Annotation, pages 24–31, Boston, MA.
  31. Moschitti, Alessandro and Roberto Basili. 2004. Complex linguistic features for text classification: A comprehensive study. In Proceedings of the 26th European Conference on Information Retrieval Research (ECIR 2004), pages 181–196, Sunderland. find
  32. Palmer, Martha, Dan Gildea, and Paul Kingsbury. 2005. The proposition bank: An annotated corpus of semantic roles. Computational Linguistics, 31(1):71–105.
  33. Pang, Bo and Lillian Lee. 2004. A sentimental education: Sentiment analysis using subjectivity summarization based on minimum cuts. In Proceedings of the 42nd Meeting of the Association for Computational Linguistics (ACL’04), Main Volume, pages 271–278, Barcelona.
  34. Pang, Bo and Lillian Lee. 2008. Opinion mining and sentiment analysis. Foundations and Trends in Information Retrieval, 2(1–2):1–135. find
  35. Pang, Bo, Lillian Lee, and Shivakumar Vaithyanathan. 2002. Thumbs up? Sentiment classification using machine learning techniques. In Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing, pages 79–86, Philadelphia, PA.
  36. Popescu, Ana-Maria and Oren Etzioni. 2005. Extracting product features and opinions from reviews. In Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, pages 339–346, Vancouver.
  37. Prasad, Rashmi, Nikhil Dinesh, Alan Lee, Eleni Miltsakaki, Livio Robaldo, Aravind Joshi, and Bonnie Webber. 2008. The Penn Discourse Treebank 2.0. In Proceedings of the 6 th International Conference on Languages Resources and Evaluations (LREC 2008), pages 2,961–2,968, Marrakech.
  38. Quirk, Randolph, Sidney Greenbaum, Geoffrey Leech, and Jan Svartvik. 1985. A Comprehensive Grammar of the English Language. Longman, New York. find
  39. Ruppenhofer, Josef, Swapna Somasundaran, and Janyce Wiebe. 2008. Finding the sources and targets of subjective expressions. In Proceedings of the Sixth International Language Resources and Evaluation (LREC’08), pages 2,781–2,788, Marrakech. find
  40. Schwartz, Richard and Steve Austin. 1991. A comparison of several approximate algorithms for finding multiple (n-best) sentence hypotheses. In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pages 701–704, Toronto. find
  41. Smith, David and Jason Eisner. 2008. Dependency parsing by belief propagation. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 145–156, Honolulu, HI.
  42. Somasundaran, Swapna, Galileo Namata, Janyce Wiebe, and Lise Getoor. 2009. Supervised and unsupervised methods in employing discourse relations for improving opinion polarity classification. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, pages 170–179, Sin…
  43. Stoyanov, Veselin and Claire Cardie. 2006. Partially supervised coreference resolution for opinion summarization through structured rule learning. In Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing, pages 336–344, Sydney.
  44. Stoyanov, Veselin and Claire Cardie. 2008. Annotating topics of opinions. In Proceedings of the Sixth International Language Resources and Evaluation (LREC’08), pages 3,213–3,217, Marrakech. find
  45. Surdeanu, Mihai, Richard Johansson, Adam Meyers, Lluı́s Màrquez, and Joakim Nivre. 2008. The CoNLL-2008 shared task on joint parsing of syntactic and semantic dependencies. In Proceedings of CoNLL 2008, pages 159–177, Manchester.
  46. Taskar, Ben, Carlos Guestrin, and Daphne Koller. 2004. Max-margin Markov networks. In Advances in Neural Information Processing Systems 16, pages 25–32, Cambridge, MA, MIT Press. find
  47. Titov, Ivan and Ryan McDonald. 2008. A joint model of text and aspect ratings for sentiment summarization. In Proceedings of ACL-08: HLT, pages 308–316, Columbus, OH.
  48. Tjong Kim Sang, Erik F., and Jorn Veenstra. 1999. Representing text chunks. In Proceedings of the Ninth Conference of the European Chapter of the Association for Computational Linguistics, pages 173–179, Bergen.
  49. Tsochantaridis, Ioannis, Thorsten Joachims, Thomas Hofmann, and Yasemin Altun. 2005. Large margin methods for structured and interdependent output variables. Journal of Machine Learning Research, 6(Sep):1453–1484. find
  50. Wiebe, Janyce, Rebecca Bruce, and Thomas O’Hara. 1999. Development and use of a gold standard data set for subjectivity classifications. In Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics, pages 246–253, College Park, MD.
  51. Wiebe, Janyce, Theresa Wilson, and Claire Cardie. 2005. Annotating expressions of opinions and emotions in language. Language Resources and Evaluation, 39(2-3):165–210. find
  52. Wiegand, Michael and Dietrich Klakow. 2010. Convolution kernels for opinion holder extraction. In Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pages 795–803, Los Angeles, CA. find
  53. Wilson, Theresa, Janyce Wiebe, and Paul Hoffmann. 2005. Recognizing contextual polarity in phrase-level sentiment analysis. In Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, pages 347–354, Vancouver.
  54. Wilson, Theresa, Janyce Wiebe, and Paul Hoffmann. 2009. Recognizing contextual polarity: An exploration of features for phrase-level sentiment analysis. Computational Linguistics, 35(3):399–433.
  55. Wu, Yuanbin, Qi Zhang, Xuangjing Huang, and Lide Wu. 2009. Phrase dependency parsing for opinion mining. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, pages 1,533–1,541, Singapore.
  56. Yu, Hong and Vasileios Hatzivassiloglou. 2003. Towards answering opinion questions: Separating facts from opinions and identifying the polarity of opinion sentences. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP-2003), pages 129–136, Sapporo.
  57. Zirn, Cäcilia, Mathias Niepert, Heiner Stuckenschmidt, and Michael Strube. 2011. Fine-grained sentiment analysis with structural features. In Proceedings of 5th International Joint Conference on Natural Language Processing, pages 336–344, Chiang Mai. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/johansson-2013-relational-features-fine-grained-opinion/