Drexel University Home Pagewww.drexel.edu DREXEL UNIVERSITY LIBRARIES HOMEPAGE >>
iDEA DREXEL ARCHIVES >>

iDEA: Drexel E-repository and Archives > Drexel Academic Community > College of Information Science and Technology > Research Day Posters (IST) > Using semantic similarity to improve user modeling in web personalization systems

Please use this identifier to cite or link to this item: http://hdl.handle.net/1860/1584

Title: Using semantic similarity to improve user modeling in web personalization systems
Authors: Achananuparp, Palakorn
Han, Hyoil
Issue Date: 20-Apr-2006
Publisher: Drexel University. College of Information Science and Technology.
Series/Report no.: IST Research Day 2006 posters
Abstract: Personalization is a process by which the users are presented with web resources customized to their interests. Critical to the personalization process is the user model which is the system’s representation of the user characteristics and preferences. However, current web personalization systems traditionally use keywords extracted from contents of visited pages as basis of the user models. The keyword extraction technique, based on vector space model, does not consider the semantics of the content which can be used to improve the characterization of the user preferences. Terms which are semantically related, such as car and vehicle, will be treated separately in keyword-based approach. In this study, we propose a method to improve user modeling in web personalization systems by incorporating the semantics of the content. To achieve that, we map keywords extracted from web pages’ content to concepts in domain ontology. The mapping is based on semantic similarity between terms in WordNet taxonomy.
URI: http://hdl.handle.net/1860/1584
Appears in Collections:Research Day Posters (IST)

Files in This Item:

File Description SizeFormat
2007021003.pdf122.81 kBAdobe PDFView/Open
View Statistics

Items in iDEA are protected by copyright, with all rights reserved, unless otherwise indicated.

 

Valid XHTML 1.0! iDEA Software Copyright © 2002-2010  Duraspace - Feedback