The acquisition of knowledge from multiple experts in the domain of sensory evaluation panel training : a thesis presented in partial fulfilment of the requirements for the degree of Master of Philosophy in Social Science (Computer Science) at Massey University, New Zealand

Abstract

Knowledge acquisition is the elicitation and representation of human expertise and is one of the first steps taken in constructing an expert system. It has often been cited as the 'bottleneck' in expert systems development due to the labour intensive processes needed to deal with the expert human. Various researchers have proposed methodologies for improving both the accuracy and the productivity of the process. This has ranged from manual to automated methods as well as examining what the expert might be thinking during a study of the conscious activity.

This research has focused on the issues involved in the manual elicitation of knowledge using multiple experts in the same domain. It utilises the transcripts of semi-structured interviews and discourse analysis techniques to construct the domain layer of a knowledge base, employing the KADS methodology.

The findings highlight the importance of the relationship between the knowledge engineer, organisation and the human experts. Issues such as motivation, organisational commitment and communication skills feature as key indicators of the likely success of an expert system development project. While automated acquisition assists with productivity, it works against the development of relationships within the project team and the trade-off must be carefully considered by the project manager.