Adaptive and Intelligent Educational Systems are interesting resources for supporting teaching-learning activities. Such environments make use of intelligent techniques to adapt educational content to the real needs of students. With the increasing amount of educational content becoming available, there is a good reason to believe that smart data analysis and machine learning techniques will become indispensable ingredients for educational progress. Therefore, this work proposes an approach for automatic and dynamic analysis of learning objects repositories in which an ontology models the relations between learning objects attributes and learning styles. Promising results have been obtained, and they are presented in this work.