Abstract
Two prominent design features of an Artificial Intelligence CAI (AI CAI) System for teaching problem-solving skills were experimentally evaluated. Seventy-six subjects were randomly assigned to four treatment groups formed by factorially combining two values each of two system design variables. The variables were the ability/lack of ability of the system to answer specific student generated questions regarding the current problem state, and the inclusion/exclusion of computer generated tutorial dialogues aimed at correcting student misprocessing of information during the solution of the problem. Analysis of the data indicated that students receiving computer generated instructional dialogues performed significantly more poorly on a transfer task than students not receiving such tutorial dialogues. The variable of student initiated questioning and the interaction of the two variables yielded non-significant results. Goal-directed production systems are reported to formally model task performance and instructional decision-making activities. The usefulness of these formal modeling techniques to instructional system design and evaluation is illustrated in a detailed analysis of the system's performance. Implications for future instructional system design techniques using the AI CAI approach are discussed.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
