JOURNAL OF SOFTWARE MAINTENANCE AND EVOLUTION: RESEARCH AND PRACTICE J. Softw. Maint. Evol.: Res. Pract. 2004; 16:129–150 (DOI: 10.1002/smr.286) Research Analysis of Web-usage behavior for focused Web sites: a case study Mohammad El-Ramly ‡ and Eleni Stroulia ∗ ,† Department of Computing Science, University of Alberta, 221 Athabasca Hall, Edmonton, Alberta, Canada T6G 2E8 SUMMARY The number of Web users and the diversity of their interests increase continuously; Web-content providers seek to infer these interests and to adapt their Web sites to improve accessibility of the offered content. Usage-pattern mining is a promising approach in support of this goal. Assuming that past navigation behavior is an indicator of the users’ interests, then, Web-server logs can be mined to infer what the users are interested in. On that basis, the Web site may be reorganized to make the interesting content more easily accessible or recommendations can be dynamically generated to help new visitors find information of interest faster. In this paper, we discuss a case study examining the effectiveness of sequential-pattern mining for understanding the users’ navigation behavior in focused Web sites. This study examines the Web site of an undergraduate course, as an example of a focused Web site that offers information intrinsically related to a process and closely reflects the workflow of this underlying process. We found that in such focused sites, indeed, visitor behavior reflects the process supported by the Web site and that sequential-pattern mining can effectively predict Web-usage behavior in these sites. Copyright c  2004 John Wiley & Sons, Ltd. KEY WORDS: H.2.8 data mining; H.3.5 online information services; Web-based services 1. INTRODUCTION AND MOTIVATION The World Wide Web contains an enormous amount of information in the form of a rather unstructured collection of hyperlinked documents. This loose and dynamic organization structure makes finding ∗ Correspondence to: Eleni Stroulia, Department of Computing Science, University of Alberta, 221 Athabasca Hall, Edmonton, Alberta, Canada T6G 2E8. † E-mail: stroulia@cs.ualberta.ca ‡ This work was conducted while the first author was a Doctoral candidate at the University of Alberta. He has since assumed a Lecturer position with the Department of Computer Science, University of Leicester, University Road, Leicester LE1 7RH, U.K. Contract/grant sponsor: IRIS-4 Contract/grant sponsor: ASERC Received 1 December 2002 Copyright c  2004 John Wiley & Sons, Ltd. Revised 11 April 2003 Accepted 30 June 2003