Diagnostic, predictive and compositional modeling with data mining in integrated learning environments

Models represent a set of generic patterns to test hypotheses. This paper presents the CogMoLab student model in the context of an integrated learning environment. Three aspects are discussed: diagnostic and predictive modeling with respect to the issues of credit assignment and scalability and comp...

Full description

Bibliographic Details
Main Author: LEE, C
Format: Article
Language:English
Published: PERGAMON-ELSEVIER SCIENCE LTD 2007
Subjects:
Online Access:http://shdl.mmu.edu.my/2985/
http://shdl.mmu.edu.my/2985/1/1015.pdf
Description
Summary:Models represent a set of generic patterns to test hypotheses. This paper presents the CogMoLab student model in the context of an integrated learning environment. Three aspects are discussed: diagnostic and predictive modeling with respect to the issues of credit assignment and scalability and compositional modeling of the student profile in the context of an intelligent tutoring system/adaptive hypermedia learning system architectural pattern. The SOM-PCA, a collaborative-based data mining approach, is shown to be reusable for all three purposes above, enabling fast, objective implementations without requiring much intensive data collection. (C) 2005 Elsevier Ltd. All rights reserved.