Strategic Learning Meta-model: A Selection Model of Learning Activities

摘要

In this work we present a Selection Model of Learning Activities (SMLA) in a Personalized Virtual Learning Environment. The SMLA consists of a model to evaluate and classify academic activities based on its difficulty, so the difficult or easy activities are replaced with other with intermediate difficulty. The SMLA is part of a Strategic Learning Metamodel that is conformed by three layers: (i) the intelligent layer that includes a personalized virtual learning environment, (ii) the infrastructure layer based on the Cloud Computing, and (iii) the regulation model that provides a control of the activities assigned to the learners based on the Full-Brain theory. We develop four experiments that implement the SMLA, and we observed that the model with activities with difficulty between 0.2 and 0.85 produces an enhancement int the academic performance of the students.