E-learning as one of the learning support can be adapted to each student's learning styles. The lack of learning objects (LOs) that can be recommended to learners is an outstanding problem. The second challenge is the recommendation of these LOs. To solve them, we implement an approach that uses Wikipedia content for the creation of new educational resources and an ontology for the modeling of students and LOs. We define the problem of LO recommendation, so a genetic algorithm is presented to solve it. Tests performed on a prototype ensure the feasibility of this approach in solving these problems.