Towards a new approach for constructing concept maps based on fuzzy logic

In recent years, adaptive learning systems rely increasingly on concept maps to customize the educational logic developed in their courses. Most approaches do not take into account the possibility of combining the concept maps predefined by experts of field and those developed automatically using the Fuzzy Sets Theory. In this article, we present a hybrid approach using on the one hand the feedback from experts of domain to select, prioritize relevant concepts and create prerequisite relationships to get the initial concept map, on the other hand we use the fuzzy logic to measure relevance degree of all relationships existing in this concept map, these links are considered as fuzzy relationships. With this approach we got two types of prerequisite relationships between concepts, the first type can be classified as relationships correctly established by the expert. These relationships must be kept in the final concept map. The second type can be considered as relationships incorrectly established by the expert, because the concepts involved in these relationships are independent, in this case these relations must be deleted or substituted with the inverse of the original relations, or because the items used in evaluations of these concepts, connected by erroneous relations, are inappropriate and must to be reviewed. Keywords—Concept map; Fuzzy Sets Theory; Adaptive Learning Environments; Fuzzy prerequisites relationships; Data mining.