Generating Domain-Specific Sentiment Lexicons for Opinion Mining

  • Zaher Salah
  • Frans Coenen
  • Davide Grossi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8346)


Two approaches to generating domain-specific sentiment lexicons are proposed: (i) direct generation and (ii) adaptation. The first is founded on the idea of generating a dedicated lexicon directly from labelled source data. The second approach is founded on the idea of using an existing general purpose lexicon and adapting this so that it becomes a specialised lexicon with respect to some domain. The operation of the two approaches is illustrated using a political opinion mining domain and evaluated using a large corpus of labelled political speeches extracted from political debates held within the UK Houses of Commons.


Domain-Specific Sentiment Lexicons Opinion Mining Sentiment Analysis 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Asmi, A., Ishaya, T.: A framework for automated corpus generation for semantic sentiment analysis. In: Proc. World Congress on Engineering (WCE 2012), pp. 436–444 (2012)Google Scholar
  2. 2.
    Grijzenhout, S., Jijkoun, V., Marx, M.: Opinion mining in dutch hansards. In: Proceedings of the Workshop From Text to Political Positions. Free University of Amsterdam (2010)Google Scholar
  3. 3.
    Esuli, A., Sebastiani, F.: SentiWordNet: A publicly available lexical resource for opinion mining. In: Proceedings from the International Conference on Language Resources and Evaluation, LREC (2006)Google Scholar
  4. 4.
    Denecke, K.: Are sentiwordnet scores suited for multi-domain sentiment classification? In: Fourth International Conference on Digital Information Management, ICDIM 2009, pp. 1–6 (2009)Google Scholar
  5. 5.
    Montejo-Raez, A., Martínez-Cámara, E., Martin-Valdivia, M., Ureña-López, L.: Random walk weighting over sentiwordnet for sentiment polarity detection on twitter. In: Proc 3rd Workshop on Computational Approaches to Subjectivity and Sentiment Analysis, pp. 3–10 (2012)Google Scholar
  6. 6.
    Ohana, B., Tierney, B.: Sentiment classification of reviews using sentiwordnet. In: Proceedings of the 9th IT & T Conference, Dublin Institute of Technology (2009)Google Scholar
  7. 7.
    Salah, Z., Coenen, F., Grossi, D.: Extracting debate graphs from parliamentary transcripts: A study directed at UK House of Commons debates. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Law (ICAIL 2013), Rome, Italy, pp. 121–130 (2013)Google Scholar
  8. 8.
    Baccianella, S., Esuli, A., Sebastiani, F.: SentiWordNet 3.0: An enhanced lexical resource for sentiment analysis and opinion mining. In: Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC 2010). European Language Resources Association, ELRA (2010)Google Scholar
  9. 9.
    Thelwall, M., Buckley, K.: Topic-based sentiment analysis for the social web: The role of mood and issue-related words. Journal of the American Society for Information Science and Technology 64(8), 1608–1617 (2013)CrossRefGoogle Scholar
  10. 10.
    Birla, V.K., Gautam, R., Shukla, V.: Retrieval and creation of domain specific lexicon from noisy text data. In: Proceedings of ASCNT-2011, CDAC, Noida, Indiaz (2011)Google Scholar
  11. 11.
    Demiroz, G., Yanikoglu, B., Tapucu, D., Saygin, Y.: Learning domain-specific polarity lexicons. In: 2012 IEEE 12th International Conference on Data Mining Workshops (ICDMW), pp. 674–679 (2012)Google Scholar
  12. 12.
    Choi, Y., Cardie, C.: Adapting a polarity lexicon using integer linear programming for domainspecific sentiment classification. In: Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, pp. 590–598 (2009)Google Scholar
  13. 13.
    Weichselbraun, A., Gindl, S., Scharl, A.: Using games with a purpose and bootstrapping to create domain-specific sentiment lexicons. In: Proceedings of the 20th ACM International Conference on Information and Knowledge Management, CIKM 2011, pp. 1053–1060. ACM, New York (2011)Google Scholar
  14. 14.
    Qiu, G., Liu, B., Bu, J., Chen, C.: Expanding domain sentiment lexicon through double propagation. In: Proceedings of the 21st International Jont Conference on Artifical Intelligence, IJCAI 2009, pp. 1199–1204. Morgan Kaufmann Publishers Inc., San Francisco (2009)Google Scholar
  15. 15.
    Lau, R., Zhang, W., Bruza, P., Wong, K.: Learning domain-specific sentiment lexicons for predicting product sales. In: 2011 IEEE 8th International Conference on e-Business Engineering (ICEBE), pp. 131–138 (2011)Google Scholar
  16. 16.
    Ringsquandl, M., Petković, D.: Expanding opinion lexicon with domain specific opinion words using semi-supervised approach. In: BRACIS 2012 - WTI, IV International Workshop on Web and Text Intelligence (2012)Google Scholar
  17. 17.
    Zhang, J., Peng, Q.: Constructing chinese domain lexicon with improved entropy formula for sentiment analysis. In: 2012 International Conference on Information and Automation (ICIA), pp. 850–855 (2012)Google Scholar
  18. 18.
    Wilks, Y., Stevenson, M.: The grammar of sense: Using part-of-speech tags as a first step in semantic disambiguation. Natural Language Engineering 4(5), 135–143 (1998)CrossRefGoogle Scholar
  19. 19.
    Kuhn, A., Ducasse, S., Gibra, T.: Semantic clustering: Identifying topics in source code. Information and Software Technology 49(3), 230–243 (2007)CrossRefGoogle Scholar
  20. 20.
    Li, H., Sun, C., Wan, K.: Clustering web search results using conceptual grouping. In: Proc. 8th International Conference on Machine Learning and Cybernetics, pp. 12–15 (2009)Google Scholar
  21. 21.
    Martineau, J., Finin, T.: Delta tfidf: An improved feature space for sentiment analysis. In: Proc 3rd International ICWSM Conference, pp. 258–261 (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Zaher Salah
    • 1
  • Frans Coenen
    • 1
  • Davide Grossi
    • 1
  1. 1.Department of Computer ScienceUniversity of LiverpoolLiverpoolUnited Kingdom

Personalised recommendations