Knowledge evolution course discovery in a professional virtual community

  • Authors:

  • Yuh-Jen Chen;Yuh-Min Chen

  • Affiliations:

  • Department of Accounting and Information Systems, National Kaohsiung First University of Science and Technology, Kaohsiung, Taiwan, ROC;Institute of Manufacturing Information and Systems, National Cheng Kung University, Tainan, Taiwan, ROC

  • Venue:
  • Knowledge-Based Systems
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Capable of providing an interactive platform for enterprise experts to create and share empirical knowledge cooperatively, professional virtual communities have arisen from the pervasive use of the Internet. This circumstance incurs an overload of information and overflow of spam messages, accounting for high-volume low-quality knowledge in virtual communities. Therefore, providing valid knowledge decision support in order to assist community members to accurately predict and supply required empirical knowledge is of priority concern in implementing tacit knowledge management in an enterprise. This work develops a technology for knowledge evolution course discovery in a professional virtual community as a decision support mechanism to discover effectively the empirical knowledge evolution course hidden inside of a professional virtual community, which can guide community members to retrieve required empirical knowledge quickly. This objective can be obtained by performing the following tasks: (i) design of an empirical knowledge management framework for professional virtual communities, (ii) definition of a knowledge evolution course model, (iii) design of a knowledge evolution course discovery process, (iv) development of techniques related to the technology for knowledge evolution course discovery, and (v) implementation and evaluation of a knowledge evolution course discovery mechanism for professional virtual communities. In developing techniques associated with the discovery of knowledge evolution course, which involves topic classification, domain dictionary construction, ontology-based topic empirical knowledge model construction, topic concept extraction and representation, and path establishment between topic concepts.