NONDIAGNOSTIC INTELLIGENT TUTORING SYSTEMS - TEACHING WITHOUT STUDENTMODELS

The keystones of traditional intelligent tutoring systems (ITSs) have been complex procedures for student diagnosis and adaptive instruction based on diagnostic data. While some of these systems have been shown to be effective, they are also very expensive to develop. This paper describes another class of ITSs, non-diagnostic ITSs, which do little or no student diagnosis, and concentrate their intelligence in other a reas. Intelligent features of non-diagnostic ITSs include: modeling of experts' reasoning processes and cognitive representations (often usi ng graphic displays), coaching based on comparison of student and expe rt performance, and replays and summaries of student performance. Whil e traditional diagnostic ITSs are usually intended to be used in a sta nd-alone fashion, non-diagnostic tutors are designed to facilitate col laborative learning among students and between teachers and students, This paper presents a framework for comparing the features of non-diag nostic and diagnostic tutors. PI number of non-diagnostic and diagnost ic ITSs are described, and data on the educational effectiveness of ea ch type of ITS is presented along with estimates of the type and level of development work required for each. Finally, obstacles to wider us e of non-diagnostic ITSs are discussed.