Problems of decision rule elicitation in a classification task

Abstract Intelligent decision support requires knowledge elicitation processes. Two primary approaches for knowledge elicitation in a multiattribute classification task are 1) direct elicitation of decision rules in the form of productions, and 2) classification of multiattribute objects by an expert as a basis for development of the underlying decision rules. This study reports an experiment using a simple classification task, to compare these two forms of knowledge elicitation. Relative consistency and complexity of the resulting rule bases are analyzed. System CLASS was used as a tool for the second approach, as well as a means of analysis for the first approach. It was found that it was easier for subjects to accomplish the task using object classification than it was to formulate production rules directly. High degrees of inconsistency and incomplete rule bases resulted when there was no computer aid for the process of knowledge elicitation.

[1]  Timothy D. Wilson,et al.  Telling more than we can know: Verbal reports on mental processes. , 1977 .

[2]  George Wright,et al.  Eliciting and modelling expert knowledge , 1987, Decision Support Systems.

[3]  John W. Payne,et al.  Task complexity and contingent processing in decision making: An information search and protocol analysis☆ , 1976 .

[4]  J. Shanteau,et al.  Livestock judges: How much information can an expert use? , 1978 .

[5]  Mark D. Grover,et al.  A Pragmatic Knowledge Acquisition Methodology , 1983, IJCAI.

[6]  Oleg I. Larichev,et al.  Systematic research into human behavior in multiattribute object classification problems , 1988 .

[7]  Robert de Hoog,et al.  Knowledge acquisition for the construction of full and contradiction free knowledge bases: Oleg I. Larichev, Helen M. Moshkovich, Eugene M. Furems, Alexander I. Mechitov and Vladimir K. Morgoev, ProGamma, Groningen, 1991. ISBN 90-5144-021-9 , 1995 .

[8]  William A. Gale.  Knowledge-Based Knowledge Acquisition for a Statistical Consulting System , 1987, Int. J. Man Mach. Stud..

[9]  Richard G. Vedder.  PC‐based expert system shells: some desirable and less desirable characteristics , 1989 .

[10]  Fabio A. Schreiber,et al.  Dynamic user profiles and flexible queries in office document retrieval systems , 1989, Decis. Support Syst..

[11]  Frederick Hayes-Roth,et al.  Building expert systems , 1983, Advanced book program.

[12]  R. Dawes,et al.  Linear models in decision making. , 1974 .

[13]  Anna Hart,et al.  Knowledge elicitation: issues and methods , 1985 .

[14]  William J. Clancey,et al.  Heuristic Classification , 1986, Artif. Intell..

[15]  A. Kitchen,et al.  Knowledge based systems in artificial intelligence , 1985, Proceedings of the IEEE.

[16]  Oleg I. Larichev,et al.  Limits to decision-making ability in direct multiattribute alternative evaluation , 1988 .

[17]  Robert W. Zmud,et al.  A Synthesis of Research on Requirements Analysis and Knowledge Acquisition Techniques , 1992, MIS Q..

[18]  Oleg I. Larichev,et al.  Decision support system class for R&D planning , 1990, Expert Planning Systems.

[19]  G. A. Miller.  THE PSYCHOLOGICAL REVIEW THE MAGICAL NUMBER SEVEN, PLUS OR MINUS TWO: SOME LIMITS ON OUR CAPACITY FOR PROCESSING INFORMATION 1 , 1956 .