Intelligent Tutor Systems and the Personalization of Pedagogical Objects in Adaptive e-Learning

The integration of new technologies has led to the emergence of personalized and adaptive learning methods. In order to provide dynamic personalized learning, learning models must update on learner knowledge, affective state, and behavior. Artificial intelligence (AI) has largely supported the development of tutoring systems, educational data mining is essential to provide information about the learning process and learner’s behavior in order to have a solid foundation for effective research on personalized systems. Intelligent Tutor Systems (ITS) correspond to a real example of personalized learning, they perform a good calibration of the contents, personalize the learning paths as close as possible to the learner, and optimize motivation. Two main families of ITS designs for personalization can be distinguished. The first, personalization, implies that all learners follow the same learning path, but at different rates. The second distinguishes a specific path that allows each learner to follow a specific learning path according to his or her responses. ITS has revolutionized personalized learning through adaptive e-learning, thanks to the progressive evaluations that are carried out throughout the learning process, which allows to target the gaps based on the creation of personalized and adapted pedagogical objects containing the strong points assimilated by the learner and providing additional explanations as well as application exercises, Adaptive Learning uses AI to personalize the content of the pedagogical objects to the needs of each learner and provide each learner with the appropriate content according to his or her level, learning styles, and strategies. From this observation, the hypothesis is that good personalization will facilitate the learning process, will increase the investment of the learners, and can be an aid to decision-making for teachers who use e-learning platforms, so our work consists in personalizing the learning path of a learner by taking into account his profile, the domain model, the pedagogical model and the interface model, which allows to personalize the pedagogical objects in the e-learning platforms, the latter will be self-feeding and self-perfecting as the training sessions are carried out. As a result, it will be able to make recommendations based on the data collected.