No abstract

E-learning is becoming the most popular educational system used in the world, the learners can easily access to the information at anywhere in anytime. The teaching methods used in this context are effective because they can combine practice and feedback, to combine collaborative activities with individualized learning, customized learning paths based on the needs of learners and to offer educational games and simulations. However, the lack of courses updates can bring some educational problems to the learner and the process of updating becomes very difficult and tiring to the tutor. This study aims to improve the learning quality by providing a good content, courses materials updated and well-structured to the learners in the one hand, and minimize the time and labor spent in the process of updating, changing the learning and looking for the content to the tutor in the other hand. The proposed system provides an automatic maintenance of updates courses by using intelligent agents.

E-learning adaptation has become the most important method that facilitates access to the appropriate content. Adaptive approaches consist of reducing the problems of incompatibilities between learner's cognitive abilities and educational content's difficulties. In some cases, the adapted curriculum cannot meet learner's skills completely seen its incoherent structure, its unsuitable methodologies and sometimes its complexity. Therefore, we need to measure the convenience of the content material to improve it and ensure learners' satisfaction. In other words, it is necessary to estimate its appropriateness to each learner. That is why; we have proceeded by using decision tree (DT) algorithm which is a supervised data mining method. It helps to predict the convenience of the proposed content material for learners. Our system consists of classifying learning material into two classes: "good" if it is convenient, and "anomaly" if not. To achieve that, we have used an intelligent agent called Classifier Agent (CLA). It tracks learner's behavior by collecting a set of attributes like score, learning time, and number of attempts, feedback and interactions with the tutor. Then, he calculates the predictive attribute by using the (DT) algorithm. The finding algorithm shows that the score is the most crucial indicator gives us more information about the conformity of curriculum to learners, followed by learning time, feedback and number of attempts.

The growth of the information and communication technologies has led to the appearance of new concepts, approach and disciplines. For learners, an e-learning system constitutes rich window to the knowledge. It presents a varied training, including different content material format (video, text, interactive content...) and diverse methods. In order to keep learners’ attention, e-learning system must provide good content's quality, including revised material and updated methods. In this perspective, we have implemented multi-agent system composed of three sort of agents ensuring a permanent revision to the e-learning content. The first one is called Checker Agent (CA). It checks the educational resources, and detects the outdated ones so as to be treated. The second agent is named Search Agent (SA). The task of this one is to look for recent contents and new teaching methods. Whereas, the third agent is called Updater Agent (UA). Its function consists on inserting the retrieved updates corresponding to each content. The communication between these agents is ensured by an XML files. In this paper, we have proposed an implementation of the first part of our system. Namely, the checking process of e-learning curriculum by implementing the CA algorithm. And the integration process by implementing the UA algorithm. As result, the tests and experimentations done in this context have proved the effectiveness of the proposed solution, and revealed positive results both in term of learning process and learners’ feedback.

No abstract