A Machine Learning Approach to Student Modeling.
Abstract
The notion of buggy procedures has played an important role in recent cognitive models of mathematical skills. The authors review some earlier work on student modeling, in which Artificial Intelligence methods have been used to automatically construct buggy models of student behavior. They then propose an alternate approach to student modeling that draws on insights from the rapidly developing field of machine learning, and describe ACN, a student modeling system that incorporates this approach. This system begins with a set of overly general rules, which it uses to search a problem space until it arrives at the same answer as the student. The ACM computer program then uses the solution path it has discovered to determine positive and negative instances of its initial rules, and employs a discrimination learning mechanism to place additional conditions on these rules. The revised rules will reproduce the solution path without search, and constitute a cognitive model of the student's behavior. The authors examine ACM's operation in the domain of multi-column subtraction problems, and propose some extensions that should be included in future versions of the system. Finally, they discuss the generality, psychological validity, and practical utility of this approach to student modeling. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- May 01, 1984
- Accession Number
- ADA141704
Entities
People
- P. Langley
- S. Ohlsson
- S. Sage
Organizations
- Carnegie Mellon University