| dc.description.abstract | Intelligent Tutoring Systems (ITSs) need to determine the quality of students' responses to provide relevant feedback. This thesis presents a systematic literature review comparing the diagnostic processes of 40 ITSs of various domains. It investigates what kinds of diagnoses are made and how they are made. It also compares the processes across domains and across four tutoring approaches: model tracing, example tracing, constraint-based and intention-based approaches. The analysis identi?ed eight aspects that ITSs diagnose: Correctness, Difference, Redundancy, Type of Error, Common Errors, Order, Preference and Time. All ITSs diagnose Correctness. Mathematics tutors diagnose Common Errors more often than programming tutors, and programming tutors diagnose Type of Error more often than
mathematics tutors. There do not seem to be any differences between approaches. A general model was made that represents all diagnostic processes. | |
