A multi-agents system to compute human learning indicators activities based on model-driven engineering approach

Abstract

This paper presents a multi-agent architecture and its implementation for facilitating the evaluation of learners' activities in real learning situations mediated by a technology enhanced learning systems. Our proposal is based on model-driven engineering using modelled activity traces to compute human learning indicators. We claim this approach facilitates the computation, the management and the reuse of learning indicators independently of any learning platform.