Context-based services selection and recommendation through P-learning platform

Taking into account continuously growing content wealth of pervasive environments generally, user needs assistance to find what he want in short time. Specifically in pervasive learning environment where learners are surrounded by numerous suppliers and the rich resources offered by the learning platform, the personalized recommender systems seems important for providing user by convenience and fulfil his needs. However, existing learning recommender systems interest to the user appraisal and taste while the contextual constraints due to the heterogeneity may influence the service consumption. We propose in this paper an hybrid recommender approach based on contextual information and memory-based filtering.