Web Behaviormetric User Profiling Concept

Authors:
Peter Géczy;Noriaki Izumi;Shotaro Akaho;Kôiti Hasida
Affiliations:
National Institute of Advanced Industrial Science and Technology (AIST), Tokyo and Tsukuba, Japan;National Institute of Advanced Industrial Science and Technology (AIST), Tokyo and Tsukuba, Japan;National Institute of Advanced Industrial Science and Technology (AIST), Tokyo and Tsukuba, Japan;National Institute of Advanced Industrial Science and Technology (AIST), Tokyo and Tsukuba, Japan
Venue:
EC-Web '08 Proceedings of the 9th international conference on E-Commerce and Web Technologies
Year:
2008

Citing 8
Cited 0

Incorporating contextual information in recommender systems using a multidimensional approach

ACM Transactions on Information Systems (TOIS)
Dynamic personalization of web sites without user intervention

Communications of the ACM - Spam and the ongoing battle for the inbox
Exploiting web browsing histories to identify user needs

Proceedings of the 12th international conference on Intelligent user interfaces
Generating semantically enriched user profiles for Web personalization

ACM Transactions on Internet Technology (TOIT)
A Web Usage Mining Framework for Mining Evolving User Profiles in Dynamic Web Sites

IEEE Transactions on Knowledge and Data Engineering
Knowledge worker intranet behaviour and usability

International Journal of Business Intelligence and Data Mining
User profiles for personalized information access

The adaptive web
Data mining for web personalization

The adaptive web

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a concept for building behaviorally centered user profiles. The concept utilizes behavioral analytics of user interactions in web environments. User interactions are temporally segmented into elemental browsing units. The browsing segments permit identification of the essential navigational points as well as higher order abstractions. The profiles incorporate relevant metrics from three major domains: temporal, navigational, and abstractions. Temporal metrics focus on aspects of durations and delays between portions of human interactions. The navigational metrics target the initial, terminal, and single user actions. The abstraction metrics encompass elemental patterns of human browsing behavior and their interconnections. The profiling concept utilizes relatively simple analytic and statistical apparatus. It facilitates computational efficiency and scalability to large user domains.