Redes bayesianas para predecir el estilo de aprendizaje de estudiantes en entornos virtuales

Abstract

Introduction: It describes the use of Bayesian Networks to implement a model of uncertainty to predict the learning style of students through their interaction in a virtual learning environment based on the Felder-Silverman model. Method: The model uncertainty was designed and developed to be integrated in the LMS Moodle. In order to validate the proposed model, an actual educational scenario was built and two groups - one from the National University of Loja and other from the International University of Ecuador - were exposed to the experiment. Results: The block "Learning Style" (EA) allowed students to visualize the probabilities of each dimension of their EA by observing that, according to their interactions, these probabilities changed. Likewise, the teachers could visualize the probabilities of EA obtained by each student when these interactions were done in the hosted virtual course enclosed in the Virtual Learning Environment. Conclusion: The proposal may serve as support for teachers who want to identify predominant learning styles of their students and, based on that, prepare activities and resources in the courses under their responsibilities.

Keywords

• Inteligencia artificial
• Modelo bayesiano
• Modelo Felder-Silverman