Development of Learning Styles and Multiple Intelligences through Particle Swarm Optimization

Adaptivity is an important aspect in computer based educational environments and one where the building of automated and intelligent systems that support it has been a challenge. In fact, the automatic detection of the pedagogical traits in order to construct a student model that allows inference of the next step in the learning process has been one of the main goals when producing adaptive systems. Learning styles and multiple intelligence theories have been widely used in student modeling to show how a student ad quires knowledge and highlights special learning abilities. Through the bringing together of these two areas of learning a picture of an individual student can be made. This information therefore becomes useful for a tutor to adapt the learning process to the student. It is therefore within this context that this study proposes an innovative method that is driven by the Kolb learning process in order to improve the intelligence percentages by bringing out in each individual those areas in which they excel, but also help in the improvement of the learning process where deficiency is detected. Thus, this method is able to detect and correct automatically the initial self-evaluation. The selection of learning objects during the learning process is carried out by a particle swarm algorithm.