| |
| With the increasing popularity of the Internet, there is a growing demand for web-based
education, which allows students to study and learn at their own pace over the Internet.
However in order to improve the teaching quality, such systems should be able to adapt the
teaching in accordance with individual students’ ability and progress. Focusing on this
objective, this paper proposes a new method to construct group-wised courseware by mining
both context and structure of the courseware to build personalized web tutor trees. To this end,
the concept of web tutor units and the notion of similarity are presented. Five algorithms,
including the Naive Algorithm for tutor concept tree and the Level-generate Algorithm to
generate web tutor units of K+1 levels are proposed. Experimental results are presented to
demonstrate the effectiveness of the new method. |
|
| Keywords:Distance learning, student profiling, web tutor unit, group-wised tutor tree. |
|
