Multi-learner System towards an Efficient E-learning System Mohammed A. Razek 1 , Claude Frasson 2 & Marc Kaltenbach 2 1 Math and Computer Science Depart. Faculty of Science, Azhar University, Nasr city 11884, Cairo, Egypt 2 Département d'informatique et de recherche opérationnelle Université de Montréal C.P. 6128, Succ. Centre-ville Montréal, Québec Canada H3C 3J7 {abdelram, frasson,kaltenba}@iro.umontreal.ca Abstract Existing multi-learner systems support three areas of group collaborative E-learning environments: communication, coordination, and collaboration. This distinction reflects the description of the functional aspects of the strict idea WYSIWIS (What You See Is What I See). Yet, this method is only of limited use because it does not take into consideration individual requirements. In other words, it lacks adaptation. Therefore, adding adaptation features to this method personalizes the course presentation to the learner's needs through learning sessions. Accordingly this leads to a new trend that we could call “What You See Is Adapted to What I Need to See” (WYSIAWINS). 1. Introduction Collaborative systems allow geographically distributed learners to work together on common tasks. There are two types of collaborative environments in the context of online learning, namely asynchronous and synchronous. Although they both fit the characteristics of collaboration, the requirements for their implementation are quite different. In an asynchronous collaboration, the interaction among learners happens indirectly through the environment. In contrast, during a synchronous collaboration the learners have to act at the same time. In this paper, we describe the architecture, implementation and deployment of the Confidence Intelligent Tutoring System (CITS). It is a synchronous and an asynchronous E-learning system providing learners and tutors with real time text conferencing, visual workspace tools, and adaptive environment. It based on a multi-agent approach support in building collaboration intelligent E-leaning system. Such system can help a community of online learners to understand each other, allow them to use visual tools to draw an example on a whiteboard, and provide them with extra updated information. This system can extract automatically knowledge about domain knowledge and about learners' behaviour during a learning discussion. Thus, it can infer the behavior of learners and adapt presentation of subject mater in order to improve their success rate in answering questions and boost their self-confidence during learning session. It uses Java client/server architecture to deal with a difficult set of networking requirements: multi-way communication with synchronous shared displays, scalable to a lot of real-time learners, and running over standard Internet servers. This paper is organized as follows. Section 2 discusses the role of the collaborative learning environment. In section 3, we describe CITS overview. In section 5, we present the evaluation conducted on CITS. And section 6 concludes the paper. 2. Collaborative Learning Environment CSCL systems can be classified in several ways. Ellis et al. [Ellis 91] suggested three areas of group interaction to support CSCL systems: communication, coordination, and collaboration. But, we think that the term of coordination could involve with collaboration aspect. Furthermore, the adaptation and awareness aspects have to be taken into consideration. In this sense, we consider four areas to support group interaction, as shown in Fig.1: • Communication. • Collaboration. • Awareness. • Adaptation. In the following, we will shed light on some basic concepts and ideas of these four areas. Proceedings of the Fifth IEEE International Conference on Advanced Learning Technologies (ICALT’05) 0-7695-2338-2/05 $20.00 © 2005 IEEE