Buranarach, Marut
(2005)
A Framework for the Organization and Discovery of Information Resources in a WWW Environment Using Association, Classification and Deduction.
Doctoral Dissertation, University of Pittsburgh.
(Unpublished)
Abstract
The Semantic Web is envisioned as a next-generation WWW environment in which information is given well-defined meaning. Although the standards for the Semantic Web are being established, it is as yet unclear how the Semantic Web will allow information resources to be effectively organized and discovered in an automated fashion. This dissertation research explores the organization and discovery of resources for the Semantic Web. It assumes that resources on the Semantic Web will be retrieved based on metadata and ontologies that will provide an effective basis for automated deduction. An integrated deduction system based on the Resource Description Framework (RDF), the DARPA Agent Markup Language (DAML) and description logic (DL) was built. A case study was conducted to study the system effectiveness in retrieving resources in a large Web resource collection. The results showed that deduction has an overall positive impact on the retrieval of the collection over the defined queries. The greatest positive impact occurred when precision was perfect with no decrease in recall. The sensitivity analysis was conducted over properties of resources, subject categories, query expressions and relevance judgment in observing their relationships with the retrieval performance. The results highlight both the potentials and various issues in applying deduction over metadata and ontologies. Further investigation will be required for additional improvement. The factors that can contribute to degraded performance were identified and addressed. Some guidelines were developed based on the lessons learned from the case study for the development of Semantic Web data and systems.
Share
Citation/Export: |
|
Social Networking: |
|
Details
Item Type: |
University of Pittsburgh ETD
|
Status: |
Unpublished |
Creators/Authors: |
|
ETD Committee: |
|
Date: |
28 January 2005 |
Date Type: |
Completion |
Defense Date: |
13 December 2004 |
Approval Date: |
28 January 2005 |
Submission Date: |
16 December 2004 |
Access Restriction: |
No restriction; Release the ETD for access worldwide immediately. |
Institution: |
University of Pittsburgh |
Schools and Programs: |
School of Information Sciences > Information Science |
Degree: |
PhD - Doctor of Philosophy |
Thesis Type: |
Doctoral Dissertation |
Refereed: |
Yes |
Uncontrolled Keywords: |
description logic; metadata; ontology; RDF; search; Semantic Web |
Other ID: |
http://etd.library.pitt.edu/ETD/available/etd-12162004-222001/, etd-12162004-222001 |
Date Deposited: |
10 Nov 2011 20:11 |
Last Modified: |
15 Nov 2016 13:54 |
URI: |
http://d-scholarship.pitt.edu/id/eprint/10391 |
Metrics
Monthly Views for the past 3 years
Plum Analytics
Actions (login required)
![View Item View Item](/style/images/action_view.png) |
View Item |