Exploratory Test of an Automated Knowledge Elicitation and Organization Tool
In IJAIED
10 (3): "'Best of ITS 98' Special Issue "
Publication information
Abstract
This paper combines the contents of two papers that were presented at the ITS '98
conference—one focusing on knowledge representation (Shute, 1998) and the other describing a
knowledge elicitation tool (Shute, Torreano, & Willis, 1998). There are three main purposes of this
paper. First, as a means to stress instructional and assessment implications of different knowledge
types, we will briefly overview knowledge representations. Second, we describe a novel cognitive
tool designed to aid in knowledge elicitation and organization for instructional purposes –
specifically geared for intelligent tutoring system development. Our aim for this tool, embodied in a
program called DNA (Decompose, Network, Assess), is to increase the efficiency of creating the
expert model, often referred to as the bottleneck in developing intelligent instructional systems.
Third, we present an exploratory test of the tool's efficacy. Specifically, we used DNA with three
statistical experts to explicate their knowledge structures related to measures of central tendency in
statistics. In short, we found that DNA shows promise as a functionally feasible program. DNA was
able to effectively elicit relevant information, commensurate with a benchmark system, generating a
starting curriculum upon which to build instruction. The initial elicitation was achieved in hours
compared to months for conventional elicitation procedures.
