Intelligent Agent-Based e-Learning System For Adaptive Learning

Hokyin Lai, City University of Hong Kong
Minhong Wang, City University of Hong Kong
Huaiqing Wang, City University of Hong Kong


Adaptive learning approach support learners to achieve the intended learning outcomes through a personalized way which is not new. Previous studies always mistake adaptive e-Learning as personalizing the presentation style of learning materials which is not totally correct. The core goal of adaptive learning is to personalize the learning content to cope with the individual differences in aptitude. This complicated logic can only be handled with an intelligent agent system, but not other technologies. In this study, an adaptive learning model is developed based on the Aptitude-Treatment Interaction theory and Constructive Alignment Model. The model aims at enhancing the intrinsic motivation of students as a first step, and then their learning outcome. This model is operationalized with a multi-agent framework and is experimented under a controlled laboratory setting. The result is quite promising. The individual difference of students, especially in the experimental group, has been narrowed significantly. Students who have difficulties in learning show significant improvement after the test.