Document Type

Dissertation

Date of Award

Spring 5-31-2007

Degree Name

Doctor of Philosophy in Information Systems - (Ph.D.)

Department

Information Systems

First Advisor

Yi-Fang Brook Wu

Second Advisor

Murray Turoff

Third Advisor

Julian M. Scher

Fourth Advisor

Vincent Oria

Fifth Advisor

Il Im

Abstract

On the Web, there are limited ways of finding people sharing similar interests or background with a given person. The current methods, such as using regular search engines, are either ineffective or time consuming. In this work, a new approach for searching people sharing similar interests from the Web, called People-Search, is presented. Given a person, to find similar people from the Web, there are two major research issues: person representation and matching persons. In this study, a person representation method which uses a person's website to represent this person's interest and background is proposed. The design of matching process takes person representation into consideration to allow the same representation to be used when composing the query, which is also a personal website. Based on this person representation method, the main proposed algorithm integrates textual content and hyperlink information of all the pages belonging to a personal website to represent a person and match persons. Other algorithms, based on different combinations of content, inlink, and outlink information of an entire personal website or only the main page, are also explored and compared to the main proposed algorithm. Two kinds of evaluations were conducted. In the automatic evaluation, precision, recall, F and Kruskal-Goodman F measures were used to compare these algorithms. In the human evaluation, the effectiveness of the main proposed algorithm and two other important ones were evaluated by human subjects. Results from both evaluations show that the People-Search algorithm integrating content and link information of all pages belonging to a personal website outperformed all other algorithms in finding similar people from the Web.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.