Explanation Provision in Knowledge-Based Systems: A Theory-Driven Approach for Knowledge Transfer Designs

Knowledge-Based Systems (KBS) have been used in industry to free experts from mundane and routine decision making, to produce comparable and consistent decisions, and to retain the expertise of knowledgeable employees who may, for many reasons, leave a company. KBS are also desired to have the capacity to transfer knowledge to less-expert users of such systems. In this paper, Adaptive Character of Thought-Rational (ACT-R) theory is used as a foundation for the design of KBS explanations for the explicit purpose of facilitating knowledge transfer to the user. ACT-R (Anderson 1993) is a theory of cognitive skill acquisition that suggests a learner must first obtain certain facts about a new learning situation (declarative memory pieces) and then convert a series of facts into a set of rules that will produce accurate problem-solving skills (procedural memory pieces). Prior research has examined pieces of the ACT theory in its earlier forms, but no comprehensive tests examining the simultaneous effect of the multiple components have previously been completed. The current study addresses three questions based on ACT-R theory: (1) Can declarative-knowledge-based explanations improve declarative knowledge transfer? (2) Can declarative-knowledge-based explanations improve procedural knowledge transfer? (3) Can procedural-knowledge-based explanations improve procedural knowledge transfer? An experiment employing eight KBS, differing by types of KBS explanation prompts, which were designed to stimulate declarative and/or procedural knowledge transfer, was conducted with 294 accounting information systems students. An analysis of the results provides some support for the use of declarative-based KBS explanations for declarative knowledge transfer, strong support for the use of declarative-based KBS explanations for procedural knowledge transfer, but a lack of support for the use of procedural-based KBS explanations for procedural knowledge transfer. The results suggest that organizations may be able to improve the efficiency and effectiveness of training programs for knowledge workers through the application of KBS that include declarative knowledge-based explanations.