Profiling Learners Behavior: A Multi-agent Approach to Support Diagnosis in Learning Management System

Learning management system has become an important role to support traditional classroom learning, e-learning and blended learning. However, learner behavior analysis is difficult because it lacks face-to-face interactions between lecturers and students in most e-learning environments. Thus, it is almost impossible to evaluate learning performance before the end of learning cycle. This study proposes a multi-agent framework to real-time monitor learners´ behavior, forecast their learning performance, and adapt proper strategies by both lecturers and students to increase learning effectiveness.