Discovery of aggregate usage profiles based on clustering information needs

Authors:
Azreen Azman;Iadh Ounis
Affiliations:
University of Glasgow, Glasgow, Scotland;University of Glasgow, Glasgow, Scotland
Venue:
Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval
Year:
2004

Citing 2
Cited 0

Towards adaptive Web sites: conceptual framework and case study

Artificial Intelligence - Special issue on Intelligent internet systems
Discovery and Evaluation of Aggregate Usage Profiles for Web Personalization

Data Mining and Knowledge Discovery

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present an alternative technique for discovering aggregate usage profiles from Web access logs. The technique is based on clustering information needs inferred from users' browsing paths. Browsing paths are extracted from users' access logs. Information need is inferred from each browsing path by using the Ostensive Model[1]. The technique is evaluated in a document recommendation application. We compare the performance of our technique against the well-established transaction-based technique proposed in [2]. Based on an initial evaluation, the results are encouraging.