A Cognitive and Ontology-Based Model for Building Glass-Box Learning-Objects 

Short description: The goal of this project was to combine the concept of "learning objects" used in the field of e-learning, with a knowledge representation model similar as the one used in Cognitive Tutors, in the field of Intelligent Tutoring Systems (ITS).

Date :  This work was done during my M.Sc. (2003-2005) based on my work on a cognitive model for ITS   that started in 2003 (see project 3). 

Description: In e-learning, a popular solution to make teaching material reusable is to design and package it as learning objects. However, learning objects are mostly "black-boxes", as they offer few information about their content and how it will be used. To adress this issue, we combined the concept of learning objects with a model for describing  cognitive processes of learners during learning activities. The proposed model allow to define learning objects that  provides enough information about their usage so that a virtual agent can offer tailored assistance during learning activites. 

The proposed model offer three layers of knowledge for the description of learning objects:

• The first layer describes the knowledge with ontologies, to facilitate the separation of the knowledge in multiple files, their interpretation as a whole, and provide a basis for logical reasoning. 
• The second layer describes cognitive processes to permit building learning objects that can be used for providing automated personnalized assistance. 
• The third layer builds learning objects upon the two first layers, by relying on current e-learning standards (IEEE LOM and IMS-CP).  

The model has been implemented, and was first applied in the RedBool tutoring systems for learning to simplify Boolean expressions [1]  [2] [3] (cf. fig. 2). More recently the model has been extended and applied in the  RomanTutor tutoring system for teaching a highly complex domain (see project 1).

Fig 2. The Redbool software [1]

Main publications

[1] Fournier-Viger P., Najjar, M., Mayers, A. & Nkambou, R. (2006). A Cognitive and Logic based Model for Building Glass-box Learning Objects. Interdisciplinary Journal of Knowledge and Learning Objects, Vol. 2. pp: 77-94.

[2] Fournier-Viger P., Najjar, M., Mayers, A. & Nkambou R. (2006). From Black-box Learning Objects to Glass-Box Learning Objects. Proc. 8th Intern. Conf. on Intelligent Tutoring Systems (ITS 2006). LNCS 4053, pp: 258-267, Springer-Verlag, Berlin.

[3] Fournier-Viger, P. (2005). Un modèle de représentation des connaissances à trois niveaux de sémantique pour les systèmes tutoriels intelligents. M.Sc. dissertation, University of Sherbrooke, Canada,  194 pages (french).

RedBool  is a software program developped by the  GDAC and ASTUS research team, that involved the participation of  many B.Sc./M.Sc/Ph.D. students at University of Sherbrooke and University of Quebec at Montreal.

Copyright © 2005-2008 Philippe Fournier-Viger. All rights reserved.