Authors: Tapan Kamdar, and Anupam Joshi

Date: November 20, 2000

Abstract: Personalization of content returned from a web site is an important problem in general, and affects e-commerce and e-services in particular. Targeting appropriate information or products to the end user can significantly change (for the better) the users experience on a web site. One possible approach to web personalization is to mine typical user profiles from the vast amount of historical data stored in access logs. In the absence of any a priori knowledge, unsupervised classification or clustering methods are ideally suited to analyze the semi-structured log data of user accesses by examining user sessions. User access profiles are generated by clustering user sessions on the basis of pair-wise dissimilarities using a robust fuzzy clustering algorithm.We present a system that mines the logs to get profiles and uses them to automatically generate a web page containing URLs the user might be interested in. We also evaluate the efficacy of sessionizing the information with and without the use of cookies.

Type: TechReport

Institution: University of Maryland, Baltimore County

Google Scholar: search

Number of downloads: 1591

Available for download as

size: 187599 bytes

Related Projects:

Past Project

 Web/Data Mining and Personalization.

Bookmark at: Digg | Del.icio.us | Connotea | CiteULike