Intelligent-systems design: development of a framework and empirical assessment of knowledge presentation and reasoning in an expert-system interface
Thesis/Dissertation
·
OSTI ID:7245041
The research investigated the role of knowledge presentation and knowledge organization (question type) in an expert system to support users' information-processing strategies for problem solving. The expert system application was computer diagnostics performed within a multinational computer manufacturer. A framework for a systematic research program for evaluating the effectiveness of intelligent interfaces was developed. The framework identified the interaction between user expertise (expert vs. novice), level of problem uncertainty, knowledge presentation format (procedural vs. declarative), question type (requiring abstract vs. concrete information organization), and decision-making process as they impact decision-making performance while using an expert system. A significant difference in performance was found between high- and low-skill users. High-skill users performed faster, more accurate, and had self-reported confidence ratings that were higher than low-skill users. Also, for both problem tasks, problem solution time decreased a greater amount for low skill users than for high skill users when using the expert system. Finally, a negative correlation was found between user confidence ratings and problem-solving performance.
- Research Organization:
- Rensselaer Polytechnic Inst., Troy, NY (USA)
- OSTI ID:
- 7245041
- Country of Publication:
- United States
- Language:
- English
Similar Records
Control and cooperation in distributed expert systems
Computer-aided knowledge engineering, a framework for building and maintaining expert systems
Development of a methodology for knowledge elicitation for building expert systems
Book
·
Fri Dec 31 23:00:00 EST 1982
·
OSTI ID:5169840
Computer-aided knowledge engineering, a framework for building and maintaining expert systems
Conference
·
Thu Dec 31 23:00:00 EST 1992
· Transactions of the American Nuclear Society; (United States)
·
OSTI ID:6946013
Development of a methodology for knowledge elicitation for building expert systems
Thesis/Dissertation
·
Wed Dec 31 23:00:00 EST 1986
·
OSTI ID:5635120