Conceptual clustering: A new approach to student modeling in Intelligent Tutoring Systems

Abstract

Student modeling is a central problem in Intelligent Tutoring Systems design and development. In this way, the characteristic that distinguishes this type of system is the ability to determine as accurately and quickly as possible the student's cognitive and affective-motivational state in order to personalize the educational process. Therefore, the fundamental problem is to select data structure to represent all relative information to student and to choose the procedure to make the diagnosis. This paper describes a model for knowledge engineering inherent to all intelligent tutoring system, using the LC-Conceptual clustering algorithm, from logical combinatorial pattern recognition. This algorithm builds the objects clusters based on their similarity, using a grouping criterion, and it also builds the property (or concept) that meets each group of objects.