Study of the Regularity of the Users’ Internet Accesses

  • Nicolas Durand
  • Luigi Lancieri
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2412)


The aim of this study is to investigate relationship between past users’ behavior (described by access patterns) and future one. The two main ideas are first to explore the possible users’ characterization that can be extracted from access pattern. This allows to measure and to have a better understanding of users’ behavior. This knowledge allows us to build new services as building interest communities based on a comparative approach and clustering. The second idea is to see if these characterizations can be useful to forecast future access. This could be useful to prefetch web data in proxy-cache. We show that there are some partial mathematical models binding the users’ behavior to the repetition of queries.


Access Pattern Temporal Coherence Past User Mining Sequential Pattern France Telecom 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Agrawal, R. and Srikant, R.: Mining Sequential Patterns: Generalizations and Performance Improvements, EDBT’96, Avignon, France (1996)Google Scholar
  2. 2.
    Mannila, H. and Toivonen, H. and Verkamo, A.I.: Discovery of Frequent Episodes in Event Sequences, Helsinki, C-1997-15 (1997)Google Scholar
  3. 3.
    Nanopoulos, A., Katsaros, D., Manolopoulos, Y.: Effective Prediction of Web-User Accesses: A Data Mining Approach, WebKDD’01 Workshop, (2001)Google Scholar
  4. 4.
    Yang, Q. and Zhang, H.H., Li, T.: Mining Web Logs for Prediction Models in WWW Caching and Prefetching, ACM SIGKDD’01, San Francisco, (2001)Google Scholar
  5. 5.
    Lancieri, L., Memory and Forgetfulness: Two Complementary Mechanisms to Characterize the Various Actors of the Internet in their Interactions, University of Caen, France, December, (2000)Google Scholar
  6. 6.
    Almeida, V. and Bestravos, A. and Crovella, M. and de Oliveira, A., Characterizing Reference Locality in the WWW, PDIS’96, Miami Beach, 1996Google Scholar
  7. 7.
    Leland, W. and Taqqu, M. and Willinger, W., Wilson, D., On the Self-SimilarNature of Ethernet Traffic, ACM SIGCOMM93, San Francisco, 183–193 (1993)Google Scholar
  8. 8.
    Paxson, V.: Fast Approximation of Self-Similar Network Traffic, University of California, Berkeley, LBL-36750 (1995)Google Scholar
  9. 9.
    Breslau, L. and Cao, P. and Fan, L. and Phillips, G. and Shenker, S.: On the Implications of Zipf’s law for Web Caching, the 3rd Int. WWW Caching Workshop (1998)Google Scholar
  10. 10.
    Legouix, S. and Foucault, J. P. and Lancieri, L.: A Method for Studying the Variability of Users’ Thematic Profile, WebNet2000 AACE, San Antonio (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Nicolas Durand
    • 1
  • Luigi Lancieri
    • 1
  1. 1.France Telecom R&DCaen

Personalised recommendations