Automatic expert identification using a text categorization technique in knowledge management systems

Abstract

Since tacit knowledge such as know-how and experiences is hard to be managed effectively using information technology, it is recently proposed that providing an appropriate expert identification mechanism in KMS to pinpoint experts in the organizations with searched expertise is more effective and efficient to utilize this type of knowledge. In this paper, we propose a framework to automate expert identification using a text categorization technique called Vector Space Model to minimize maintenance cost of expert profiles as well as problems related to incorrectness and obsolescence resulted from subjective manual profile processing. Also, we define the structure of expertise consisting of activeness, relevance, and usefulness factors to enable deriving the overall expertise level of experts by analyzing knowledge artifacts registered to the knowledge base. The developed prototype system, “Knowledge Portal for Researchers in Science and Technology”, is introduced to show the applicability of the proposed framework.