Intelligent search for experts using fuzzy abstraction hierarchy in knowledge management systems

In knowledge management systems (KMS), managing explicit knowledge is comparatively easy using information technology such as databases. However, tacit knowledge, usually possessed by human experts in unstructured forms such as know-how and experiences, is hard to systemize. Recent research has shown that it is more effective to provide search mechanisms for experts than to directly search for specific knowledge itself in KMS to pinpoint experts with needed knowledge in the organizations so that users can acquire the knowledge from the found experts. In this article, we propose an intelligent search framework to provide search capabilities for experts who not only match search conditions exactly but also belong to the similar or related subject fields according to the user needs. In enabling intelligent searches for experts, the Fuzzy Abstraction Hierarchy (FAH) framework has been adopted. Based on FAH, searching for experts with similar or related expertise is facilitated using the subject field hierarchy defined in the system. While adopting FAH, a text categorization approach based on Vector Space Model is also utilized to overcome the limitation of the original FAH framework. To test applicability and practicality of the proposed framework, the prototype system, "Knowledge Portal for Researchers in Science and Technology" sponsored by the Ministry of Science and Technology (MOST) of Korea, has been developed.
Publisher
IGI PUBL
Issue Date
2007-07
Language
ENG
Keywords

TEXT CATEGORIZATION; INFORMATION; ONTOLOGIES; RETRIEVAL; TECHNOLOGY; MODEL; WEB

Citation

JOURNAL OF DATABASE MANAGEMENT, v.18, no.3, pp.47 - 68

ISSN
1063-8016
URI
http://hdl.handle.net/10203/5038
Appears in Collection
KSIM-Journal Papers(저널논문)
  • Hit : 378
  • Download : 6
  • Cited 0 times in thomson ci
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡClick to seewebofscience_button
⊙ Cited 1 items in WoSClick to see citing articles inrecords_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0