PSO-ASent: Feature Selection Using Particle Swarm Optimization for Aspect Based Sentiment Analysis

  • Deepak Kumar Gupta
  • Kandula Srikanth Reddy
  • Shweta
  • Asif EkbalEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9103)


The amount of user generated online contents has increased dramatically in the recent past. The phenomenal growth of e-commerce has led to a significantly large number of reviews for a product or service. This provides useful information to the users to take a fully informed decision on whether to acquire the service and/or product or not. In this paper we present a method for automatic feature selection for aspect term extraction and sentiment classification. The proposed approach is based on the principle of Particle Swarm Optimization (PSO) and performs feature selection within the learning framework of Conditional Random Field (CRF). Experiments on the benchmark set up of SemEval-2014 Aspect based Sentiment Analysis Shared Task show the F-measure values of 81.91 % and 72.42 % for aspect term extraction in the laptop and restaurant domains, respectively. The method yields the classification accuracies of 78.48 % for the restaurant and 71.25 % for the laptop domain. Comparisons with the baselines and other existing systems show that our proposed approach attains the promising accuracies with much reduced feature sets in all the settings.


Aspect extraction Sentiment analysis Feature selection Conditional random field Particle Swarm Optimization 


  1. 1.
    Hu, M., Liu, B.: Mining and summarizing customer reviews. In: Proceedings of the 10th KDD, Seattle, WAs, pp. 168–177 (2004)Google Scholar
  2. 2.
    Liu, B.: Sentiment Analysis and Opinion Mining. Synthesis Lectures on Human Language Technologies. Morgan & Claypool Publishers (2012)Google Scholar
  3. 3.
    Brody, S., Elhadad, N.: An unsupervised aspect-sentiment model for online reviews. In: Proceedings of NAACL, Los Angeles, CA, pp. 804–812 (2010)Google Scholar
  4. 4.
    Kim, S.M., Hovy, E.: Determining the sentiment of opinions. In: Proceedings of the 20th International Conference on Computational Linguistics, p. 1367. Association for Computational Linguistics (2004)Google Scholar
  5. 5.
    Turney, P.D.: Thumbs up or thumbs down?: semantic orientation applied to unsupervised classification of reviews. In: Proceedings of the 40th ACL, pp. 417–424 (2002)Google Scholar
  6. 6.
    Jagtap, V., Pawar, K.: Analysis of different approaches to sentence-level sentiment classification. Int. J. Sci. Eng. Technol. 2, 164–170 (2013). ISSN: 2277–1581Google Scholar
  7. 7.
    Moghaddam, S., Ester, M.: Aspect-based opinion mining from online reviews. In: Tutorial at SIGIR Conference (2012)Google Scholar
  8. 8.
    Popescu, A.M., Etzionir, O.: Extracting product features and opinions from reviews. In: Proceedings of the Conference on HLT/EMNLP, pp. 339–346 (2005)Google Scholar
  9. 9.
    Blair-Goldensohn, S., Hannan, K., McDonald, R., Neylon, T., Reis, G.A., Reynar, J.: Building a sentiment summarizer for local service reviews. In: WWW Workshop on NLP in the Information Explosion Era, vol. 14 (2008)Google Scholar
  10. 10.
    Zhuang, L., Jing, F., Zhu, X.Y.: Movie review mining and summarization. In: Proceedings of the 15th ACM International Conference on Information and Knowledge Management, CIKM 2006 (2006)Google Scholar
  11. 11.
    Mukherjee, A., Liu, B.: Aspect extraction through semi-supervised modeling. In: Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers, ACL 2012, vol. 1, pp. 339–348 (2012)Google Scholar
  12. 12.
    Fahrni, A., Klenner, M.: Old wine or warm beer: target-specic sentiment analysis of adjectives. In: Symsposium on Affective Language in Human and Machine, The Society for the Study of Artificial Intelligence and Simulation of Behavior (AISB), pp. 60–63 (2008)Google Scholar
  13. 13.
    Pontiki, M., Galanis, D., Pavlopoulos, J., Papageorgiou, H., Androutsopoulos, I., Manandhar, S.: Semeval-2014 task 4: aspect based sentiment analysis. In: Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), Dublin, Ireland, August 2014Google Scholar
  14. 14.
    Kennedy, J., Eberhart, R.C.: Swarm Intelligence. Morgan Kaufmann Publishers Inc., San Francisco (2001)Google Scholar
  15. 15.
    Lafferty, J.D., McCallum, A., Pereira, F.C.N.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: ICML, pp. 282–289 (2001)Google Scholar
  16. 16.
    Goldberg, D.E.: Genetic Algorithms in Search, Optimization and Machine Learning, 1st edn. Addison-Wesley Longman Publishing Co. Inc., Boston (1989)zbMATHGoogle Scholar
  17. 17.
    Kirkpatrick, S., Gelatt, C.D., Vecchi, M.P.: Optimization by simulated annealing. SCIENCE 220(4598), 671–680 (1983)zbMATHCrossRefMathSciNetGoogle Scholar
  18. 18.
    Kennedy, J., Kennedy, J.F., Eberhart, R.C.: Swarm Intelligence. Morgan Kaufmann, San Francisco (2001)Google Scholar
  19. 19.
    Shi, Y., Eberhart, R.: A modified particle swarm optimizer. In: IEEE World Congress on Computational Intelligence, pp. 69–73. IEEE (1998)Google Scholar
  20. 20.
    Toh, Z., Wang, W.: DLIREC: aspect term extraction and term polarity classification system. In: Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), pp. 235–240 (2014)Google Scholar
  21. 21.
    Miller, G.A.: WordNet: a lexical database for English. Commun. ACM 38(11), 39–41 (1995)CrossRefGoogle Scholar
  22. 22.
    Brown, P.F., Desouza, P.V., Mercer, R.L., Pietra, V.J.D., Lai, J.C.: Class-based n-gram models of natural language. Comput. Linguist. 18(4), 467–479 (1992)Google Scholar
  23. 23.
    Hatzivassiloglou, V., McKeown, K.R.: Predicting the semantic orientation of adjectives. In: Proceedings of the ACL/EACL, pp. 174–181 (1997)Google Scholar
  24. 24.
    Wiebe, J., Mihalcea, R.: Word sense and subjectivity. In: Proceedings of the COLING/ACL, pp. 1065–1072 (2006)Google Scholar
  25. 25.
    Ding, X., Liu, B., Yu, P.S.: A holistic lexicon-based approach to opinion mining. In: Proceedings of the 2008 International Conference on Web Search and Data Mining, WSDM 2008 (2008)Google Scholar
  26. 26.
    Brun, C., Popa, D.N., Roux, C.: XRCE: hybrid classification for aspect-based sentiment analysis. In: SemEval 2014, pp. 838–842 (2014)Google Scholar
  27. 27.
    Chernyshevich, M.: IHS R&D belarus: cross-domain extraction of product features using conditional random fields, pp. 309–313 (2014)Google Scholar
  28. 28.
    Wagner, J., Arora, P., Cortes, S., Barman, U., Bogdanova, D., Foster, J., Tounsi, L.: DCU: aspect-based polarity classification for semeval task 4. In: Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), pp. 223–229 (2014)Google Scholar
  29. 29.
    Kiritchenko, S., Zhu, X., Cherry, C., Mohammad, S.: NRC-Canada-2014: detecting aspects and sentiment in customer reviews. In: Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014) (2014)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Deepak Kumar Gupta
    • 1
  • Kandula Srikanth Reddy
    • 1
  • Shweta
    • 1
  • Asif Ekbal
    • 1
    Email author
  1. 1.Computer Science and EngineeringIndian Institute of Technology PatnaPatnaIndia

Personalised recommendations