A General Fuzzy-Based Framework for Text Representation and Its Application to Text Categorization

  • Son Doan
  • Quang-Thuy Ha
  • Susumu Horiguchi
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4223)


In this paper we develop the general framework for text representation based on fuzzy set theory. This work is extended from our original ideas [5],[4], in which a document is represented by a set of fuzzy concepts. The importance degree of these fuzzy concepts characterize the semantics of documents and can be calculated by a specified aggregation function of index terms. Based on this representation, a general framework is proposed and applied to text categorization problem. An algorithm is given in detail for choosing fuzzy concepts. Experiments on the real-world data set show that the proposed method is superior to the conventional method for text representation in text categorization.


Information Retrieval Text Categorization Aggregation Function Vector Space Model Text Representation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Billhardt, H., Bonajo, D., Maojo, V.: A context vector model for information retrieval. Journal of the American Society for Information Science and Technology (JASIST) 53(3), 236–249 (2002)CrossRefGoogle Scholar
  2. 2.
    Buell, D.A.: An analysys of some fuzzy subsets application to information retrieval systems. Fuzzy Sets and Systems 7(1), 35–42 (1982)MATHCrossRefMathSciNetGoogle Scholar
  3. 3.
    Deerwester, S., Furnas, G.W., Dumais, S., Landauer, T.K.: Indexing by latent semantic indexing. Journal of the American Society for Information Science and Technology (JASIST) 41(6), 391–407 (1990)CrossRefGoogle Scholar
  4. 4.
    Doan, S.: A fuzzy-based approach to text representation in text categorization. In: Proceeding of 14th IEEE Int’l. Conference on Fuzzy Systems - FUZZ-IEEE 2005, Nevada, U.S., pp. 1008–1013 (2005)Google Scholar
  5. 5.
    Doan, S., Horiguchi, S.: A new text representation using fuzzy concepts in text categorization. In: Proceeding of 1st International Conference on Fuzzy Set and Knowledge Discovery (FSKD), Singapore, vol. 2, pp. 514–518 (2002)Google Scholar
  6. 6.
    CMU Text Learning Group. 20newsgroups dataset, http://www.cs.cmu.edu/~textlearning
  7. 7.
    Joachims, T.: Text categorization with support vector machines: Learning with many relevant features. In: Proceedings 10th European Conference on Machine Learning (ECML), pp. 137–142 (1998)Google Scholar
  8. 8.
    Lewis, D.: Representation and Learning in Information Retrieval. PhD thesis, Graduate School of the University of Massachusetts (1991)Google Scholar
  9. 9.
    Lucarella, D., Marara, R.: First: fuzzy informatioon retrieval system. Journal of Information Science 17(2), 81–91 (1991)CrossRefGoogle Scholar
  10. 10.
    Manning, C.D., Schutze, H.: Foundations of Statistical Natural Language Processing. MIT Press, Cambridge (1999)MATHGoogle Scholar
  11. 11.
    Miyamoto, S.: Fuzzy Sets in Information Retrieval and Cluster Analysis. Kluwer Academic Publishers, Dordrecht (1990)MATHGoogle Scholar
  12. 12.
    Molinari, A., Pasi, G.: A fuzzy representation of html document for information retrieval system. In: Proceeding of 5th IEEE Int’l. Conference on Fuzzy Systems, pp. 107–112 (1996)Google Scholar
  13. 13.
    Moulinier, I.: A framework for comparing text categorization approaches. In: AAAI Symposium on Machine Learning and Information Access. Stanford University (1996)Google Scholar
  14. 14.
    Moulinier, I., Ganascia, J.G.: Applying an existing machine learning algorithm to text categorization. In: Wermter, S., Riloff, E., Schaler, G. (eds.) Connectionist, Statistical and Symbolic Approaches to Learning for Natural Language Processing, pp. 343–354. Springer, Heidelberg (1996)Google Scholar
  15. 15.
    Murai, T., Miyakoshi, M., Shimbo, M.: A fuzzy document retrieval method based on two-valued indexing. Fuzzy Sets and Systems 30(2), 103–120 (1989)MATHCrossRefMathSciNetGoogle Scholar
  16. 16.
    Rocchio, J.: Relevance feedback in information retrieval. In: Salton, G. (ed.) The SMART retrieval system: Experiments on Automatic Document Processing, ch. 14, pp. 313–323. Prentice-Hall, Englewood Cliffs (1971)Google Scholar
  17. 17.
    Salton, G., Buckley, C.: Term weighting approaches in automatic text retrieval. Information Processing and Management 24(5), 513–523 (1988)CrossRefGoogle Scholar
  18. 18.
    Salton, G., Wong, A., Yang, C.S.: A vector space model for automatic indexing. Communications of the ACM 18(11), 613–620 (1975)MATHCrossRefGoogle Scholar
  19. 19.
    Sebastiani, F.: Machine learning in automated text categorization. ACM computing survey 34(1), 1–47 (2002)CrossRefGoogle Scholar
  20. 20.
    Sparck-Jones, K.A.: A statistical interpretation of term specifility and its application in retrieval. Journal of Documentation 28(1), 11–20 (1972)CrossRefGoogle Scholar
  21. 21.
    Witte, R., Bergler, S.: Fuzzy coreference resolution for summarization. In: Proceedings of 2003 International Symposium on Reference Resolution and Its Applications to Question Answering and Summarization (ARQAS), Venice, Italy, June 23–24, 2003, pp. 43–50. Università Ca’ Foscari (2003), http://rene-witte.net
  22. 22.
    Yang, Y.: An evaluation of statistical approaches to text categorization. Information Retrieval Journal 1, 69–90 (1999)CrossRefGoogle Scholar
  23. 23.
    Yang, Y., Pedersen, J.O.: A comparative study on feature selection in text categorization. In: Proceeding of the 14th International Conference on Machine Learning (ICML 1997), pp. 412–420 (1997)Google Scholar
  24. 24.
    Zadeh, L.A.: Fuzzy sets. Information Control 8, 338–353 (1965)MATHCrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Son Doan
    • 1
  • Quang-Thuy Ha
    • 2
  • Susumu Horiguchi
    • 1
  1. 1.Graduate School of Information ScienceTohoku UniversitySendaiJapan
  2. 2.College of TechnologyVietnam National UniversityHanoiVietnam

Personalised recommendations