ECAI-2002 Conference Paper

[full paper]

A multi-agent and emergent approach to learner modelling

Carine Webber, Sylvie Pesty, Nicolas Balacheff

User modelling has been a central issue in the development of user-adaptive systems, which behaviour is usually based on the user's preferences, goals, interests and knowledge. This is particularly the case when the user is a student and the system is a computer-based learning environment. The aim of this paper is to present a mechanism for diagnosing and modelling learner's conceptions based on a theoretical model of conceptions. Our approach takes the diagnosis of learner's conceptions as the emergent result of the collective actions of agents sharing an environment, transforming it and as a consequence influencing new actions. We apply techniques from voting theory for group-decision-making. This approach is at the core of the design of a distance learning platform for the learning of geometry.

Keywords: User Modeling, Multi-Agent Systems, Cognitive Modelling

Citation: Carine Webber, Sylvie Pesty, Nicolas Balacheff: A multi-agent and emergent approach to learner modelling. In F. van Harmelen (ed.): ECAI2002, Proceedings of the 15th European Conference on Artificial Intelligence, IOS Press, Amsterdam, 2002, pp.98-102.