Article in Proceedings INPROC-2005-07

BibliographyBürklen, Susanne; Marrón, Pedro José; Fritsch, Serena; Rothermel, Kurt: User Centric Walk: An Integrated Approach for Modeling the Browsing Behavior of Users on the Web.
In: IEEE Computer Society Press (ed.): Proceedings of the 38th IEEE Annual Simulation Symposium (ANSS'05), San Diego, CA, USA.
University of Stuttgart : Collaborative Research Center SFB 627 (Nexus: World Models for Mobile Context-Based Systems).
english.
San Diego, CA, USA: IEEE Computer Society Press, April 1, 2005.
Article in Proceedings (Conference Paper).
CR-SchemaG.3 (Probability and Statistics)
I.6 (Simulation and Modeling)
H.1 (Models and Principles)
KeywordsBrowsing behavior model; heavy tailed distribution
Abstract

The performance evaluation of Web applications usually requires the utilization of sequences of user requests for determined Web pages. These sequences can be obtained, for example, by applying empirical methods (recording the real sequence of requests), or by applying a formal model for generating synthetic results. In this paper, we present our Web Browsing Model and the User Centric Walk algorithm as its implementation. By taking into account the hyperlink structure as well as the different user behavior on the Web, this algorithm allows us to generate accurate synthetic data that can be used instead of empirically obtained requests. As another contribution of this paper we have shown, based on empirical data, that the probability of choosing some hyperlink from a given page as well as the probability a user leaves a page without following a hyperlink is best characterized by a power-law. Moreover, we show the flexibility and applicability of our model by performing the required correlations to empirical data, which validate our approach.

ContactContact: buerklen@informatik.uni-stuttgart.de
Department(s)University of Stuttgart, Institute of Parallel and Distributed Systems, Distributed Systems
Project(s)SFB-627, A2 (University of Stuttgart, Institute of Parallel and Distributed Systems, Distributed Systems)
Entry dateDecember 13, 2004
   Publ. Department   Publ. Institute   Publ. Computer Science