Learning Objects: Adaptive Retrieval through Learning Styles

Nowadays, the amount of information grows in an exponential way, mainly because of technological advances in media. This scenario claims for the development of different skills in order to increase learning abilities, making them personal and customizable. Such factor is significant in a changing society, which implies in a range of mechanisms which would allow to identify, in a non-intrusive way, which learning style some specific student would prefer to perform in order to build knowledge from some learning object under a learning context. This requires defining some strategies in order to recognize adult learner’s learning styles for some specific learning context. This work is based on theoretical references of Felder, Kolb and Gardner, proposing the implementation of a metadata annotation to identificate prime learning styles that are present in specific learning objects. This classification constitutes a starting point to recover learning objects from a repository according to apprentice’s profile and experiences. As a result, the effectiveness of the use of learning objects will be improved.