Testing a Cancer Meta Spider

Hsinchun Chen, Haiyan Fan, Michael Chau, Dajun Zeng

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

As in many other applications, the rapid proliferation and unrestricted Web-based publishing of health-related content have made finding pertinent and useful healthcare information increasingly difficult. Although the development of healthcare information retrieval systems such as medical search engines and peer-reviewed medical Web directories has helped alleviate this information and cognitive overload problem, the effectiveness of these systems has been limited by low search precision, poor presentation of search results, and the required user search effort. To address these challenges, we have developed a domain-specific meta-search tool called Cancer Spider. By leveraging post-retrieval document clustering techniques, this system aids users in querying multiple medical data sources to gain an overview of the retrieved documents and locating answers of high quality to a wide spectrum of health questions. The system presents the retrieved documents to users in two different views: (1) Web pages organized by a list of key phrases, and (2) Web pages clustered into regions discussing different topics on a two-dimensional map (self-organizing map). In this paper, we present the major components of the Cancer Spider system and a user evaluation study designed to evaluate the effectiveness and efficiency of our approach. Initial results comparing Cancer Spider with NLM Gateway, a premium medical search site, have shown that they achieved comparable performances measured by precision, recall, and F-measure. Cancer Spider required less user searching time, fewer documents that need to be browsed, and less user effort.

Original languageEnglish (US)
Pages (from-to)755-776
Number of pages22
JournalInternational Journal of Human Computer Studies
Volume59
Issue number5
DOIs
StatePublished - Nov 2003

Fingerprint

Spiders
Websites
cancer
Health
Information retrieval systems
Self organizing maps
Testing
Search engines
World Wide Web
Neoplasms
Delivery of Health Care
Directories
Search Engine
Information Storage and Retrieval
Information Systems
Cluster Analysis
premium
health
information retrieval
search engine

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Experimental and Cognitive Psychology

Cite this

Testing a Cancer Meta Spider. / Chen, Hsinchun; Fan, Haiyan; Chau, Michael; Zeng, Dajun.

In: International Journal of Human Computer Studies, Vol. 59, No. 5, 11.2003, p. 755-776.

Research output: Contribution to journalArticle

Chen, Hsinchun ; Fan, Haiyan ; Chau, Michael ; Zeng, Dajun. / Testing a Cancer Meta Spider. In: International Journal of Human Computer Studies. 2003 ; Vol. 59, No. 5. pp. 755-776.
@article{09dd3579c64740118c28e6a054bda3f4,
title = "Testing a Cancer Meta Spider",
abstract = "As in many other applications, the rapid proliferation and unrestricted Web-based publishing of health-related content have made finding pertinent and useful healthcare information increasingly difficult. Although the development of healthcare information retrieval systems such as medical search engines and peer-reviewed medical Web directories has helped alleviate this information and cognitive overload problem, the effectiveness of these systems has been limited by low search precision, poor presentation of search results, and the required user search effort. To address these challenges, we have developed a domain-specific meta-search tool called Cancer Spider. By leveraging post-retrieval document clustering techniques, this system aids users in querying multiple medical data sources to gain an overview of the retrieved documents and locating answers of high quality to a wide spectrum of health questions. The system presents the retrieved documents to users in two different views: (1) Web pages organized by a list of key phrases, and (2) Web pages clustered into regions discussing different topics on a two-dimensional map (self-organizing map). In this paper, we present the major components of the Cancer Spider system and a user evaluation study designed to evaluate the effectiveness and efficiency of our approach. Initial results comparing Cancer Spider with NLM Gateway, a premium medical search site, have shown that they achieved comparable performances measured by precision, recall, and F-measure. Cancer Spider required less user searching time, fewer documents that need to be browsed, and less user effort.",
author = "Hsinchun Chen and Haiyan Fan and Michael Chau and Dajun Zeng",
year = "2003",
month = "11",
doi = "10.1016/S1071-5819(03)00118-6",
language = "English (US)",
volume = "59",
pages = "755--776",
journal = "International Journal of Human Computer Studies",
issn = "1071-5819",
publisher = "Academic Press Inc.",
number = "5",

}

TY - JOUR

T1 - Testing a Cancer Meta Spider

AU - Chen, Hsinchun

AU - Fan, Haiyan

AU - Chau, Michael

AU - Zeng, Dajun

PY - 2003/11

Y1 - 2003/11

N2 - As in many other applications, the rapid proliferation and unrestricted Web-based publishing of health-related content have made finding pertinent and useful healthcare information increasingly difficult. Although the development of healthcare information retrieval systems such as medical search engines and peer-reviewed medical Web directories has helped alleviate this information and cognitive overload problem, the effectiveness of these systems has been limited by low search precision, poor presentation of search results, and the required user search effort. To address these challenges, we have developed a domain-specific meta-search tool called Cancer Spider. By leveraging post-retrieval document clustering techniques, this system aids users in querying multiple medical data sources to gain an overview of the retrieved documents and locating answers of high quality to a wide spectrum of health questions. The system presents the retrieved documents to users in two different views: (1) Web pages organized by a list of key phrases, and (2) Web pages clustered into regions discussing different topics on a two-dimensional map (self-organizing map). In this paper, we present the major components of the Cancer Spider system and a user evaluation study designed to evaluate the effectiveness and efficiency of our approach. Initial results comparing Cancer Spider with NLM Gateway, a premium medical search site, have shown that they achieved comparable performances measured by precision, recall, and F-measure. Cancer Spider required less user searching time, fewer documents that need to be browsed, and less user effort.

AB - As in many other applications, the rapid proliferation and unrestricted Web-based publishing of health-related content have made finding pertinent and useful healthcare information increasingly difficult. Although the development of healthcare information retrieval systems such as medical search engines and peer-reviewed medical Web directories has helped alleviate this information and cognitive overload problem, the effectiveness of these systems has been limited by low search precision, poor presentation of search results, and the required user search effort. To address these challenges, we have developed a domain-specific meta-search tool called Cancer Spider. By leveraging post-retrieval document clustering techniques, this system aids users in querying multiple medical data sources to gain an overview of the retrieved documents and locating answers of high quality to a wide spectrum of health questions. The system presents the retrieved documents to users in two different views: (1) Web pages organized by a list of key phrases, and (2) Web pages clustered into regions discussing different topics on a two-dimensional map (self-organizing map). In this paper, we present the major components of the Cancer Spider system and a user evaluation study designed to evaluate the effectiveness and efficiency of our approach. Initial results comparing Cancer Spider with NLM Gateway, a premium medical search site, have shown that they achieved comparable performances measured by precision, recall, and F-measure. Cancer Spider required less user searching time, fewer documents that need to be browsed, and less user effort.

UR - http://www.scopus.com/inward/record.url?scp=0242366065&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0242366065&partnerID=8YFLogxK

U2 - 10.1016/S1071-5819(03)00118-6

DO - 10.1016/S1071-5819(03)00118-6

M3 - Article

AN - SCOPUS:0242366065

VL - 59

SP - 755

EP - 776

JO - International Journal of Human Computer Studies

JF - International Journal of Human Computer Studies

SN - 1071-5819

IS - 5

ER -