Using consensus susceptibility and consistency measures for inconsistent knowledge management

  • Authors:
  • Ngoc Thanh Nguyen;Michal Malowiecki

  • Affiliations:
  • Institute of Information Science and Engineering, Wroclaw University of Technology, Poland;Institute of Information Science and Engineering, Wroclaw University of Technology, Poland

  • Venue:
  • PAKDD'05 Proceedings of the 9th Pacific-Asia conference on Advances in Knowledge Discovery and Data Mining
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

Conflicts may appear during knowledge processing, where some knowledge pieces are different but they refer to the same subject. Consensus methods are useful in processing inconsistent knowledge. However, for almost conflict situations consensus may be determined but it is not always sensible. In this paper we investigate the aspect of reasonableness of consensus. For this aim we define two notions: consensus susceptibility and consistency measure. Owing to them one may get to know when it is worth to determine a consensus for a conflict. We show the dependencies between consistency and the consensus susceptibility for conflict situations. Some results of the analysis are presented.