Title: Adaptive web presence and evolution through web log analysis

Authors: Xueping Li, Laigang Song, Alberto Garcia-Diaz

Addresses: Intelligent Information and Systems Laboratory, Department of Industrial and Information Engineering, University of Tennessee, Knoxville, 408 East Stadium Hall, Knoxville, TN 37996-0700, USA. ' Department of Industrial and Information Engineering, University of Tennessee, Knoxville, 404 East Stadium Hall, Knoxville, TN 37996-0700, USA. ' Department of Industrial and Information Engineering, University of Tennessee, Knoxville, 416 East Stadium Hall, Knoxville, TN 37996-0700, USA

Abstract: With the rapid growth of the World Wide Web and the intensified competition among the businesses, effective web presence is critical to attract potential customers and retain current customers thus to the success of the business. This paper presents a framework to establish adaptive web presence and evolution through web log analysis. Some simple yet effective descriptive statistical techniques are used to reveal the relationship between the web traffic workload and a few factors such as the domains names and geographic locations. Correspondence analysis is explored to further unveil the patterns between the web workload and user groups. We find that the power law distribution can be applied to model the web traffic. These regularities and patterns shed light on how to design a better web and enhance its performance. The implications of applying these findings to e-commerce and other websites are discussed.

Keywords: web mining; web presence; electronic commerce; world wide web; WWW; correspondence analysis; internet; e-commerce; web log analysis; blogs; blog analysis; web traffic; user groups.

DOI: 10.1504/IJECRM.2008.020408

International Journal of Electronic Customer Relationship Management, 2008 Vol.2 No.3, pp.195 - 214

Published online: 22 Sep 2008 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article