Searching and ranking method of relevant resources by user intention on the Semantic Web

Myungjin Lee, Wooju Kim, Sangun Park

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

As the information on the Internet dramatically increases, more and more limitations in information searching are revealed, because web pages are designed for human use by mixing content with presentation. In order to overcome these limitations, the Semantic Web, based on ontology, was introduced by W3C to bring about significant advancement in web searching. To accomplish this, the Semantic Web must provide search methods based on the different relationships between resources. In this paper, we propose a semantic association search methodology that consists of the evaluation of resources and relationships between resources, as well as the identification of relevant information based on ontology, a semantic network of resources and properties. The proposed semantic search method is based on an extended spreading activation technique. In order to evaluate the importance of a query result, we propose weighting methods for measuring properties and resources based on their specificity and generality. From this work, users can search semantically associated resources for their query, confident that the information is valuable and important. The experimental results show that our method is valid and efficient for searching and ranking semantic search results.

Original languageEnglish
Pages (from-to)4111-4121
Number of pages11
JournalExpert Systems with Applications
Volume39
Issue number4
DOIs
Publication statusPublished - 2012 Mar 1

Fingerprint

Semantic Web
Semantics
Ontology
Websites
Chemical activation
Association reactions
Internet

All Science Journal Classification (ASJC) codes

  • Engineering(all)
  • Computer Science Applications
  • Artificial Intelligence

Cite this

@article{8c3abeb432144cf0aa0b836c3093ae55,
title = "Searching and ranking method of relevant resources by user intention on the Semantic Web",
abstract = "As the information on the Internet dramatically increases, more and more limitations in information searching are revealed, because web pages are designed for human use by mixing content with presentation. In order to overcome these limitations, the Semantic Web, based on ontology, was introduced by W3C to bring about significant advancement in web searching. To accomplish this, the Semantic Web must provide search methods based on the different relationships between resources. In this paper, we propose a semantic association search methodology that consists of the evaluation of resources and relationships between resources, as well as the identification of relevant information based on ontology, a semantic network of resources and properties. The proposed semantic search method is based on an extended spreading activation technique. In order to evaluate the importance of a query result, we propose weighting methods for measuring properties and resources based on their specificity and generality. From this work, users can search semantically associated resources for their query, confident that the information is valuable and important. The experimental results show that our method is valid and efficient for searching and ranking semantic search results.",
author = "Myungjin Lee and Wooju Kim and Sangun Park",
year = "2012",
month = "3",
day = "1",
doi = "10.1016/j.eswa.2011.09.127",
language = "English",
volume = "39",
pages = "4111--4121",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Limited",
number = "4",

}

Searching and ranking method of relevant resources by user intention on the Semantic Web. / Lee, Myungjin; Kim, Wooju; Park, Sangun.

In: Expert Systems with Applications, Vol. 39, No. 4, 01.03.2012, p. 4111-4121.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Searching and ranking method of relevant resources by user intention on the Semantic Web

AU - Lee, Myungjin

AU - Kim, Wooju

AU - Park, Sangun

PY - 2012/3/1

Y1 - 2012/3/1

N2 - As the information on the Internet dramatically increases, more and more limitations in information searching are revealed, because web pages are designed for human use by mixing content with presentation. In order to overcome these limitations, the Semantic Web, based on ontology, was introduced by W3C to bring about significant advancement in web searching. To accomplish this, the Semantic Web must provide search methods based on the different relationships between resources. In this paper, we propose a semantic association search methodology that consists of the evaluation of resources and relationships between resources, as well as the identification of relevant information based on ontology, a semantic network of resources and properties. The proposed semantic search method is based on an extended spreading activation technique. In order to evaluate the importance of a query result, we propose weighting methods for measuring properties and resources based on their specificity and generality. From this work, users can search semantically associated resources for their query, confident that the information is valuable and important. The experimental results show that our method is valid and efficient for searching and ranking semantic search results.

AB - As the information on the Internet dramatically increases, more and more limitations in information searching are revealed, because web pages are designed for human use by mixing content with presentation. In order to overcome these limitations, the Semantic Web, based on ontology, was introduced by W3C to bring about significant advancement in web searching. To accomplish this, the Semantic Web must provide search methods based on the different relationships between resources. In this paper, we propose a semantic association search methodology that consists of the evaluation of resources and relationships between resources, as well as the identification of relevant information based on ontology, a semantic network of resources and properties. The proposed semantic search method is based on an extended spreading activation technique. In order to evaluate the importance of a query result, we propose weighting methods for measuring properties and resources based on their specificity and generality. From this work, users can search semantically associated resources for their query, confident that the information is valuable and important. The experimental results show that our method is valid and efficient for searching and ranking semantic search results.

UR - http://www.scopus.com/inward/record.url?scp=82255179219&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=82255179219&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2011.09.127

DO - 10.1016/j.eswa.2011.09.127

M3 - Article

AN - SCOPUS:82255179219

VL - 39

SP - 4111

EP - 4121

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 4

ER -