Knowledge discOvery And daTa minINg inteGrated (KOATING) Moderators for collaborative projects

Abstract

A major issue in any multidiscipline collaborative project is how to best share and simultaneously exploit different types of expertise, without duplicating efforts or inadvertently causing conflicts or loss of efficiency through misunderstanding of individual or shared goals. Moderators are knowledge based systems designed to support collaborative teams by raising awareness of potential problems or conflicts. However, the functioning of a Moderator is limited by the knowledge it has about the team members. Knowledge acquisition, learning and updating of knowledge are the major challenges for a Moderator's implementation. To address these challenges a Knowledge discOvery And daTa minINg inteGrated (KOATING) framework is presented for Moderators to enable them to continuously learn from the operational databases of the company and semi-automatically update their knowledge about team members. This enables the reuse of discovered knowledge from operational databases within collaborative projects. The integration of knowledge discovery in database (KDD) techniques into the existing Knowledge Acquisition Module of a moderator enables hidden data dependencies and relationships to be utilised to facilitate the moderation process. The architecture for the Universal Knowledge Moderator (UKM) shows how Moderators can be extended to incorporate a learning element which enables them to provide better support for virtual enterprises. Unified Modelling Language diagrams were used to specify the ways to design and develop the proposed system. The functioning of a UKM is presented using an illustrative example.