Abstract
A deep, fine-grain analysis of rhetorical structure highlights crucial sentiment-carrying text segments.
- Baccianella, S., Esuli, A., and Sebastiani, F. SentiWordNet 3.0: An enhanced lexical resource for sentiment analysis and opinion mining. In Proceedings of the Seventh Conference on International Language Resources and Evaluation (Valletta, Malta, May 19--21). European Language Resources Association, Paris, France, 2010, 2200--2204.Google Scholar
- Bal, D., Bal, M., van Bunningen, A., Hogenboom, A., Hogenboom, F., and Frasincar, F. Sentiment analysis with a multilingual pipeline. In Proceedings of the 12th International Conference on Web Information System Engineering (Sydney, Australia, Oct. 12--14) Volume 6997 of Lecture Notes in Computer Science. Springer, Berlin, Germany, 2011, 129--142. Google ScholarDigital Library
- Baldridge, J. and Morton, T. OpenNLP, 2004; http://opennlp.sourceforge.net/Google Scholar
- Chardon, B., Benamara, F., Mathieu, Y., Popescu, V., and Asher, N. Measuring the effect of discourse structure on sentiment analysis. In Proceedings of the 14th International Conference on Intelligent Text Processing and Computational Linguistics (University of the Aegean, Samos, Greece, Mar. 24--30) Volume 7817 of Lecture Notes in Computer Science. Springer, Berlin, Germany, 2013, 25--37. Google ScholarDigital Library
- Chenlo, J., Hogenboom, A., and Losada, D. Rhetorical structure theory for polarity estimation: An experimental study. Data and Knowledge Engineering 94, B (Nov. 2014), 135--147.Google Scholar
- Feldman, R. Techniques and applications for sentiment analysis. Commun. ACM 56, 4 (Apr. 2013), 82--89. Google ScholarDigital Library
- Fellbaum, C. WordNet: An Electronic Lexical Database. MIT Press, Cambridge, MA, 1998.Google ScholarCross Ref
- Heerschop, B., Goossen, F., Hogenboom, A., Frasincar, F., Kaymak, U., and de Jong, F. Polarity analysis of texts using discourse structure. In Proceedings of the 20th ACM Conference on Information and Knowledge Management (Glasgow, U.K., Oct. 24--28). ACM Press, New York, 2011, 1061--1070. Google ScholarDigital Library
- Hernault, H., Prendinger, H., duVerle, D., and Ishizuka, M. HILDA: A discourse parser using support vector machine classification. Dialogue and Discourse 1, 3 (Dec. 2010), 1--33.Google ScholarCross Ref
- Jansen, B., Zhang, M., Sobel, K., and Chowdury, A. Twitter power: Tweets as electronic word of mouth. Journal of the American Society for Information Science and Technology 60, 11 (Nov. 2009), 2169--2188. Google ScholarDigital Library
- Kim, S. and Hovy, E. Determining the sentiment of opinions. In Proceedings of the 20th International Conference on Computational Linguistics (University of Geneva, Switzerland, Aug. 23--27). Association for Computational Linguistics, Stroudsburg, PA, 2004, 1367--1373. Google ScholarDigital Library
- Kim, S. and Hovy, E. Automatic identification of pro and con reasons in online reviews. In Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics (Sydney, Australia, July 17--21). Association for Computational Linguistics, Stroudsburg, PA, 2006, 483--490. Google ScholarDigital Library
- Mann, W. and Thompson, S. Rhetorical structure theory: Toward a functional theory of text organization. Text 8, 3 (Jan. 1988), 243--281.Google ScholarCross Ref
- Manning, C., Grow, T., Grenager, T., Finkel, J., and Bauer, J. Stanford Tokenizer, 2010; http://nlp.stanford.edu/software/tokenizer.shtmlGoogle Scholar
- Marcu, D. The rhetorical parsing of unrestricted texts: A surface-based approach. Computational Linguistics 26, 3 (Sept. 2000), 395--448. Google ScholarDigital Library
- Melville, P., Sindhwani, V., and Lawrence, R. Social media analytics: Channeling the power of the blogosphere for marketing insight. In Proceedings of the First Workshop on Information in Networks (New York, Sept. 25--26, 2009); http://www.prem-melville.com/publications/Google Scholar
- Pang, B. and Lee, L. A sentimental education: Sentiment analysis using subjectivity summarization based on minimum cuts. In Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (Barcelona, Spain, July 21--26). Association for Computational Linguistics, Stroudsburg, PA, 2004, 271--280. Google ScholarDigital Library
- Pang, B. and Lee, L. Opinion mining and sentiment analysis. Foundations and Trends in Information Retrieval 2, 1 (Jan. 2008), 1--135. Google ScholarDigital Library
- Pang, B., Lee, L., and Vaithyanathan, S. Thumbs up? Sentiment classification using machine learning techniques. In Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing (Honolulu, HI, Oct. 25--27). Association for Computational Linguistics, Stroudsburg, PA, 2002, 79--86. Google ScholarDigital Library
- Sayeed, A., Boyd-Graber, J., Rusk, B., and Weinberg, A. Grammatical structures for word-level sentiment detection. In Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Montreal, Canada, July 3--8). Association for Computational Linguistics, Stroudsburg, PA, 2012, 667--676. Google ScholarDigital Library
- Socher, R., Perelygin, A., Wu, J., Chuang, J., Manning, C., Ng, A., and Potts, C. Recursive deep models for semantic compositionality over a sentiment treebank. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing (Seattle, WA, Oct. 18--21). Association for Computational Linguistics, Stroudsburg, PA, 2013, 1631--1642.Google Scholar
- Somasundaran, S., Namata, G., Wiebe, J., and Getoor, L. 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 (Singapore, Aug. 6--9). Association for Computational Linguistics, Stroudsburg, PA, 2009, 170--179. Google ScholarDigital Library
- Soricut, R. and Marcu, D. Sentence-level discourse parsing using syntactic and lexical information. In Proceedings of the Human Language Technology and North American Association for Computational Linguistics Conference (Edmonton, Canada, May 27--June 1). Association for Computational Linguistics, Stroudsburg, PA, 2003, 149--156. Google ScholarDigital Library
- Taboada, M., Voll, K., and Brooke, J. Extracting Sentiment as a Function of Discourse Structure and Topicality Technical Report 20. Simon Fraser University, Burnaby, B.C. Canada, 2008; http://www.cs.sfu.ca/research/publications/techreports/#2008Google Scholar
- Walenz, B. and Didion, J. OpenNLP, 2008; http://jwordnet.sourceforge.net/Google Scholar
Index Terms
- Using rhetorical structure in sentiment analysis
Recommendations
Rhetorical Structure Theory for polarity estimation
Sentiment analysis tools often rely on counts of sentiment-carrying words, ignoring structural aspects of content. Natural Language Processing has been fruitfully exploited in text mining, but advanced discourse processing is still nonpervasive for ...
Exploiting Hierarchical Discourse Structure for Review Sentiment Analysis
IALP '13: Proceedings of the 2013 International Conference on Asian Language ProcessingThe overall sentiment of a text is critically affected by its discourse structure. For the first time, this paper incorporates hierarchical discourse structure into an unsupervised sentiment analysis framework. Experimental results show that by ...
Sentiment analysis based on rhetorical structure theory: Learning deep neural networks from discourse trees
Highlights- Improves sentiment analysis with discourse trees from rhetoric structure theory.
AbstractProminent applications of sentiment analysis are countless, covering areas such as marketing, customer service and communication. The conventional bag-of-words approach for measuring sentiment merely counts term frequencies; however, ...
Comments