Toward More Cooperative Intelligent Distance Learning Environments
Mohammed Abdel Razek, Claude Frasson, Marc Kaltenbach · 2008
In this paper, we propose a multi-agent approach to enhance collaboration between learners. We define a Confidence Agent to be introduced in Intelligent Tutoring System (ITS) for adapting and improving the quality and efficiency of its teaching. To achieve this goal, we propose a Confidence Intelligent Tutoring System (CITS) able to manage negotiations within a community of on-line learners and improve interactions among the participants. The proposed system can extract knowledge in a domain and about learners behaviour during a learning discussion. Therefore, it infers the behaviour of learners, and adapts the presentation of the subject matter in order to improve their success rate in answering questions and increase their self-confidence during the learning session. We discuss architectural problems of the CITS and their solutions.