Cognitive Computation

, Volume 7, Issue 4, pp 487–499 | Cite as

Concept-Level Sentiment Analysis with Dependency-Based Semantic Parsing: A Novel Approach

  • Basant Agarwal
  • Soujanya Poria
  • Namita Mittal
  • Alexander Gelbukh
  • Amir Hussain
Article

Abstract

Sentiment analysis from unstructured natural language text has recently received considerable attention from the research community. In the frame of biologically inspired machine learning approaches, finding good feature sets is particularly challenging yet very important. In this paper, we focus on this fundamental issue of the sentiment analysis task. Specifically, we employ concepts as features and present a concept extraction algorithm based on a novel concept parser scheme to extract semantic features that exploit semantic relationships between words in natural language text. Additional conceptual information of a concept is obtained using the ConceptNet ontology: Concepts extracted from text are sent as queries to ConceptNet to extract their semantics. We select important concepts and eliminate redundant concepts using the Minimum Redundancy and Maximum Relevance feature selection technique. All selected concepts are then used to build a machine learning model that classifies a given document as positive or negative. We evaluate our concept extraction approach using a benchmark movie review dataset provided by Cornell University and product review datasets on books, DVDs, and electronics. Comparative experimental results show that our proposed approach to sentiment analysis outperforms existing state-of-the-art methods.

Keywords

Sentiment analysis Semantic parser Dependency rules Minimum Redundancy and Maximum Relevance feature selection ConceptNet 

References

  1. 1.
    Cambria E, Hussain A. Sentic album: content, concept, and context-based online personal photo management system. Cogn Comput. 2012;4(4):477–96.CrossRefGoogle Scholar
  2. 2.
    Poria S, Cambria E, Hussain A, Huang G-B. Towards an intelligent framework for multimodal affective data analysis. Neural Netw. 2015;63:104–16.PubMedCrossRefGoogle Scholar
  3. 3.
    Howard N, Cambria E. Intention awareness: improving upon situation awareness in human-centric environments. Hum Centric Comput Inf Sci. 2013;3(9):1–17.Google Scholar
  4. 4.
    Cambria E, Hussain A, Durrani T, Havasi C, Eckl C, Munro J. Sentic computing for patient centered applications. In: IEEE ICSP, Beijing; 2010. p. 1279–1282.Google Scholar
  5. 5.
    Cambria E, Hussain A, Havasi C, Eckl C, Munro J. Towards crowd validation of the UK national health service. In: ACM WebSci, Raleigh; 2010.Google Scholar
  6. 6.
    Liu B. Sentiment analysis and opinion mining. Synthesis lectures on human language technologies. San Rafael: Morgan & Claypool Publishers; 2012.Google Scholar
  7. 7.
    Erik C, Amir H, Catheine H, Chris E. Common sense computing: From the society of mind to digital intuition and beyond. In: Lecture notes in computer science 5707, Springer; 2009. p. 252–259.Google Scholar
  8. 8.
    Cambria E, Gastaldo P, Bisio F, Zunino R. An ELM-based model for affective analogical reasoning. Neurocomputing. 2015;149:443–55.CrossRefGoogle Scholar
  9. 9.
    Guyon I, Elisseeff A. An introduction to variable and feature selection. J Mach Learn Res. 2003;3(1):1157–82.Google Scholar
  10. 10.
    Agarwal B, Mittal N. Enhancing performance of sentiment analysis by semantic clustering of features. IETE J Res. 2014;60(6):414–22.CrossRefGoogle Scholar
  11. 11.
    Peng H, Long F, Ding C. Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell. 2005;27(8):1226–38.PubMedCrossRefGoogle Scholar
  12. 12.
    Agarwal B, Mittal N. Prominent feature extraction for review analysis: an empirical study. J Exp Theor Artif Intell. 2014. doi:10.1080/0952813X.2014.97783.
  13. 13.
    Hougue N, Bhattacharyya DK, Kalita JK. MIFS-ND: a mutual information-based feature selection method. Expert Syst Appl. 2014;41(4):6371–85.Google Scholar
  14. 14.
    Pang B, Lee L, Vaithyanathan S. Thumbs up? Sentiment classification using machine learning techniques. In: Proceedings of EMNLP; 2002. p. 79–86.Google Scholar
  15. 15.
    Matsumoto S, Takamura H, Okumura M. Sentiment classification using word sub-sequences and dependency sub-trees. In: Proceedings of PAKDD; 2005. p. 301–311.Google Scholar
  16. 16.
    Pak A, Paroubek P. Text representation using dependency tree sub-graphs for sentiment analysis. DASFAA workshop; 2011. p. 323–332.Google Scholar
  17. 17.
    Nakagawa T, Inui K, Kurohashi S. Dependency tree-based sentiment classification using CRFs with hidden variables. In: Proceeding HLT ’10 human language technologies: annual conference of the North American chapter of the association for computational linguistics; 2010. p. 786–794.Google Scholar
  18. 18.
    Xia R, Zong C, Li S. Ensemble of feature sets and classification algorithms for sentiment classification. J Inf Sci. 2011;181(6):1138–52.CrossRefGoogle Scholar
  19. 19.
    Riloff E, Patwardhan S, Janyce W. Feature subsumption for opinion analysis. In: EMNLP; 2006. p. 440–448.Google Scholar
  20. 20.
    Joshi M, Penstein-Rose C. Generalizing dependency features for opinion mining. In: ACL; 2009. p. 313–316.Google Scholar
  21. 21.
    Mejova Y, Srinivasan P. Exploring feature definition and selection for sentiment classifiers. In: Proceedings of the fifth international AAAI conference on weblogs and social media; 2011. p. 546–549.Google Scholar
  22. 22.
    Mullen T, Collier N. Sentiment analysis using support vector machines with diverse information sources. In: EMNLP; 2004. p. 412–418.Google Scholar
  23. 23.
    Osgood CE, Succi GJ, Tannenbaum PH. The measurement of meaning. Champaign: University of Illinois Press; 1957.Google Scholar
  24. 24.
    Turney PD. Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews. ACL-2002; 2002. p. 417–424.Google Scholar
  25. 25.
    Dang Y, Zhang Y, Chen H. A lexicon enhanced method for sentiment classification: an experiment on online product reviews. IEEE Intell Syst. 2010;25(4):46–53.CrossRefGoogle Scholar
  26. 26.
    Gelfand B, Wulfekuler M, Punch WF. Automated concept extraction from plain text. In: AAAI workshop on text categorization; 1998. p. 13–17.Google Scholar
  27. 27.
    Hatzivassiloglou V, McKeown KR. Predicting the semantic orientation of adjectives. In: ACL; 1997. p. 174–181.Google Scholar
  28. 28.
    Sidorov G, Velasquez F, Stamatatos E, Gelbukh A, Chanona-Hernandez L. Syntactic n-grams as machine learning features for natural language processing. Expert Syst Appl. 2014;41(3):853–60.CrossRefGoogle Scholar
  29. 29.
    Sidorov G. Non-continuous syntactic n-grams. Polibits. 2013;48(1):67–75.Google Scholar
  30. 30.
    de Marneffe M-C, Manning CD. The stanford typed dependencies representation. In: Coling 2008: proceedings of the workshop on cross-framework and cross-domain parser evaluation. Association for Computational Linguistics; 2008. p. 1–8.Google Scholar
  31. 31.
    Soujanya P, Basant A, Alexander G, Amir H, Newton H. Dependency-based semantic parsing for concept-level text analysis. In: CICLing 2014; 2014. p. 113–27.Google Scholar
  32. 32.
    Poria S, Cambria E, Winterstein G, Huang G-B. Sentic patterns: dependency-based rules for concept-level sentiment analysis. Knowl Based Syst. 2014;69:45–63.CrossRefGoogle Scholar
  33. 33.
    Havasi C, Speer R, Alonso JB. Conceptnet 3: a flexible, multilingual semantic network for common sense knowledge. In: Recent advances in natural language processing; 2007. p. 27–29.Google Scholar
  34. 34.
    Wang Q-F, Cambria E, Liu C-L, Hussain A. Common sense knowledge for handwritten Chinese text recognition. Cogn Comput. 2013;5(2):234–42.CrossRefGoogle Scholar
  35. 35.
    Manning CD, Raghvan P, Schutze H. Introduction to information retrieval. Cambridge: Cambridge University Press; 2008.CrossRefGoogle Scholar
  36. 36.
    Pang B, Lee L. A sentimental education: sentiment analysis using subjectivity summarization based on minimum cuts. In: Proceedings of the association for computational linguistics (ACL); 2004. p. 271–278.Google Scholar
  37. 37.
    Blitzer J, Dredze M, Pereira F. Biographies, bollywood, boom-boxes and blenders: domain adaptation for sentiment classification. In: ACL; 2007. p. 440–447.Google Scholar
  38. 38.
    Xia R, Zong C. Exploring the use of word relation features for sentiment classification. In: COLING-2010; 2010. p. 1336–1344.Google Scholar
  39. 39.
    Prabowo R, Thelwall M. Sentiment analysis: a combined approach. J Informetr. 2009;3(2):143–57.CrossRefGoogle Scholar
  40. 40.
    O’Keefe T, Koprinska I. Feature selection and weighting methods in sentiment analysis. In: Proceedings of the 14th Australasian document computing symposium, Sydney, Australia, ACL; 2009.Google Scholar
  41. 41.
    Ng V, Dasgupta S, Arifin SM. Examining the role of linguistic knowledge sources in the automatic identification and classification of reviews. In: Proceedings of the COLING/ACL 2006 main conference poster sessions; 2006. p. 611–618.Google Scholar
  42. 42.
    Tu Z, Jiang W, Liu Q, Lin S. Dependency forest for sentiment analysis. In: First CCF conference, natural language processing and Chinese computing; 2012. p 69–77.Google Scholar
  43. 43.
    Abbasi A. Intelligent feature selection for opinion classification. IEEE Intell Syst. 2010;25(4):75–9.Google Scholar
  44. 44.
    Abbasi A, Chen H, Salem A. Sentiment analysis in multiple languages: feature selection for opinion classification in Web forums. ACM Trans Inf Syst. 2008;26(3):12.CrossRefGoogle Scholar
  45. 45.
    Poria S, Gelbukh A, Cambria E, Hussain A, Huang G-B. EmoSenticSpace: a novel framework for affective common-sense reasoning. Knowl Based Syst. 2014;69:108–23.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2015

Authors and Affiliations

  • Basant Agarwal
    • 1
  • Soujanya Poria
    • 2
  • Namita Mittal
    • 1
  • Alexander Gelbukh
    • 3
  • Amir Hussain
    • 2
  1. 1.Department of Computer Science and EngineeringMNITJaipurIndia
  2. 2.Department of Computing Science and MathematicsUniversity of StirlingStirlingUK
  3. 3.Centro de Investigación en ComputaciónInstituto Politécnico NacionalMexico CityMexico

Personalised recommendations