Re-ranking of Retrieved Web Pages, Based on User Preference

  • Toyohide Watanabe
  • Kenji Matsuoka
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 4)


Generally, it is difficult to retrieve only Web-pages just appropriate to our retrieval purpose, even if we were very smart experts who can compose well-specified queries. In order to resolve this problem intelligently, many researchers have investigated the advanced retrieval methods which satisfy user’s requests with feedback control mechanism from retrieval results. However, since in the traditional researches the feedback control mechanism in which users do not directly operate or judge is used, un-necessary operational loads are imposed on users. In this paper, we propose a new re-ranking method based on user actions, which indicate whether the retrieved pages are relevant to their preferences or not: this method does not impose un-necessary operational loads on users, but provides easily operations which can indicate his/her preference appropriately. In addition, a means for modifying the existing queries by intended words is addressed and our method makes it possible to infer the words which are included in target Web-pages.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Jansen, B.J., Spink, A., Saracevic, T.: Real life, Real users, and Real Needs: A Study and Analysis of User Queries on the Web. Information Processing and Management 36(2), 207–227 (2000)CrossRefGoogle Scholar
  2. 2.
    Miller, G.A.: The Magical Number Seven, Plus or Minus Two: Some Limits on our Capacity for Processing Information. The Psychological Review 63, 81–97 (1956)CrossRefGoogle Scholar
  3. 3.
    Fang, H., Tao, T., Zhai, C.: A Formal Study of Information Retrieval Heuristics. In: Proc. of 27th Int’l. Conf. ACM SIGIR, pp. 49–56 (2004)Google Scholar
  4. 4.
    Krovetz, R., Croft, W.B.: Lexical Ambiguity and Information Retrieval. ACM Trans.on Information Systems (TOIS) 10(2), 115–141 (1992)CrossRefGoogle Scholar
  5. 5.
    Rocchio, J.J.: Relevance Feedback in Information Retrieval. The Smart Retrieval System- Experiments in Automatic Document Processing, 313–323 (1971)Google Scholar
  6. 6.
    Onoda, T., Murata, H., Yamada, S.: SVM-based Interactive Document Retrieval with Active Learning. New Generation Computing 26(1), 49–61 (2008)zbMATHCrossRefGoogle Scholar
  7. 7.
    Onoda, T., Murata, H., Yamada, S.: One Class Classification Methods Based on Non-Relevance Feedback Document Retrieval. In: Proc. of 2006 IEEE/WIC/ACM Int’l. Conf. on Web Intelligence and Intelligent Agent Technology, pp. 393–396 (2006)Google Scholar
  8. 8.
    Yamamoto, T., Nakamura, S., Tanaka, K.: Rerank-By-Example: Efficient Browsing of Web Search Results. In: Wagner, R., Revell, N., Pernul, G. (eds.) DEXA 2007. LNCS, vol. 4653, pp. 801–810. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  9. 9.
    Karube, T., Shizuki, B., Tanaka, J.: A Ranking Interface Based on Interactive Evaluation of Search Results. In: Proc.of WISS 2007 (2007) (in Japanese)Google Scholar
  10. 10.
    Jeh, G., Widom, J.: Scaling Personalized Web Search. In: Proc. of 12th World Wide Web Conference (WWW), pp. 271–279 (2003)Google Scholar
  11. 11.
    Matsuo, Y., Ishizuka, M.: Keyword Extraction from a Document Using Word Co-occurrence Statiscal Information. Journal of Japanese Society for Artificial Intelligence 17(3), 213–227 (2002) (in Japanese)Google Scholar

Copyright information

© Springer Berlin Heidelberg 2010

Authors and Affiliations

  • Toyohide Watanabe
    • 1
  • Kenji Matsuoka
    • 1
  1. 1.Department of Systems and Social Informatics, Graduate School of Information ScienceNagoya UniversityNagoyaJapan

Personalised recommendations