Multi-agent system for expert evaluation of learning objects from repository

Abstract

Regarding the educational contexts based on e-learning, Learning Objects (LOs) have arisen as a new conceptual model to organize the content. Thus, it is necessary to analyze the potential impact of LOs on knowledge appropriation processes using the quality concept. In this case, quality is understood as the level of relevance of the educational resources in the teachinglearning process, associated to educational goal and other characteristics. The level of significance can be determined by evaluating the characteristics of the object by a group of experts; however, this process is not an easy task because different criteria should be considered, such as teaching, interoperability, scalability and reusability. On the other hand, a factor to solve is the selection of experts. This paper presents different dimensions and metrics to evaluate, and an automatic mechanism for the correct selection of the experts. The validation is done through the development a multi-agent system.