Application of mobile agents in web-based student modelling : a thesis presented in partial fulfilment of the requirements for the degree of Master of Science in Information Systems at Massey University

Abstract

In recent years, educational information on the web has increased exponentially, and web-based learning environments are becoming mainstream applications on the Internet. But these environments face some common deficiencies, such as slow access, no adaptivity to individual student, limitation by bandwidth, and so on, which need to be resolved. Meanwhile, the research in Intelligent Agents technology has received a lot of attention in Information Systems Research and Development area. This project investigated mobile agents technology and its benefits, and applied this technology to address the problems that limit the potential of web-based learning environments. This project has developed a system, using mobile agents technology, to capture interactions over the Internet and to provide a continuous interaction pattern for a given student, even in off-line mode or in the case of unreliable connection. The mobile agents technology is used as the communications channel between client and server instead the traditional approaches. The system uses two step student modelling architecture, which consists of the local and central individual student models and central group student model. There are primarily three parts of student model in the system: local individual student model that resides in student's machine, central individual student model that resides on the central server, and central group student model that sits on the central server. This two-step modelling mechanism largely improves capturing interactions of a given student in the web-based learning environment, even in off-line mode, and enables the system to provide adaptation at different granularity. The combination of two-fold student modelling and mobile agents technology provides an attractive alternative to implement and improve web-based learning environments. The methodology used in this system addresses the problem of adaptation, which is one of the main bottlenecks that limit the development of web-based intelligent educational systems.