AGENT-BASED ADAPTIVE LEARNING MODEL FOR INTERMITTENT INTERNET CONNECTION CONDITIONS

Abstract

any scholars are interested in and are determined to improve the e-learning learning mode and provide easy access to learning information for various groups and individuals. There is need to incorporate into learning systems the ability to dynamically classify learners as they go on with the learning process. Learner classification is used to adaptively provide relevant information for the various categories of learners. There is also need to allow learners to learn while they are either on-line or off-line. In many parts of the world, especially in the developing world, most people do not have reliable continuous Internet connections. This paper reports a prototype that implements an adaptive presentation of course content under conditions of intermittent Internet connections. This prototype was tested in February 2011 by two groups of undergraduate students studying a database systems course. One group used it online and a control group used it offline. This study found out that it is possible to have learner models that can adapt to learner characteristics such as learner’s level of knowledge and that learners can be able to learn under in both on-line and off-line modes with adaptation working correctly.