Application of agents in information personalization

Pao Yue-kong Library Electronic Theses Database

Application of agents in information personalization

 

Author: Lee, Wing-yiu Vincent
Title: Application of agents in information personalization
Degree: M.Sc.
Year: 2000
Subject: Web search engines
World Wide Web
Hong Kong Polytechnic University -- Dissertations
Department: Multi-disciplinary Studies
Dept. of Computing
Pages: vii, 76 leaves : ill. ; 30 cm
Language: English
InnoPac Record: http://library.polyu.edu.hk/record=b1517929
URI: http://theses.lib.polyu.edu.hk/handle/200/4348
Abstract: This paper describes SearchTheWeb, an agent-based system that aims to provide personalization of information on the Web. In the system, agents that understand the interest of users are employed to find information on behalf of users from the Web. Agents are chosen because they possess three important characteristics: autonomous, able to learn and flexible to be deployed. SearchTheWeb models the Web as many separate areas of information domains which are composed of graphs of web pages. The information domains are in parallel to the different areas of human interests. The information personalization process is achieved by the combination of three areas:- information discovery, information filtering and information presentation. Information discovery finds out potential relevant pages on the Web. To improve efficiency during the process of finding information and minimize network resources, existing search facilities such as keywords-based search engines (e.g. Alta-Vista, Infoseek, Excite, etc...) and human-compiled directory (Open Directory) are used. Information filtering determines whether a web page is relevant and also how relevant it is to the information domains by applying information retrieval methods. Three common methods are used: Term Frequency (TF), Term frequency inversed document frequency (TFIDF) and nearest-neighbour algorithm. Instead of requiring a user to specify whether a page is interesting, SearchTheWeb performs two levels of filtering on a web page. The first level categorizes the document into the most relevant category of common interest to build up the personal profile. The second level compares the document against the personal profile of the users. Information presentation displays and summarizes the information found to users according to the degree of relevancy to the user's interests.

Files in this item

Files Size Format
b15179291.pdf 2.766Mb PDF
Copyright Undertaking
As a bona fide Library user, I declare that:
  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
  3. I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.

     

Quick Search

Browse

More Information