Evaluation System for E-Learning with Pattern Mining Tools

Authors

Abstract

Learning in online open networking environments turned out possible by today's widespread use of Internet technologies, has led to the development of a broad range of products for web-based courses at University level. However, although elearning in education is well established, there are a few attempts to extract information during the course final evaluation phase. In other words, while evaluation of e-learning applications has boosted the need to design effective methodologies for better tools, little attention was devoted to extract information for discovery of student's behavior.
In this paper, we use weblog-based framework to analyze the navigational behavior in the students' evaluation phase of a purpose-built e-learning course. An important feature of this framework is that extraction of behavior is achieved by building selective models of pattern mining. Our approach uses semisupervised and supervised learning techniques, such as, neural networks (NN) and Support Vector Machines (SVM), to build prediction models able to track student's behavior. The data sets were obtained from student's logs in a Moodle designed Course at the University level. The results show the model is able to successfully predict students' final outcome while bringing useful feedback during course learning.

Keywords

Pattern Mining; E-Learning; Neural Networks; Support Vector Machines (SVM)

Subject

Pattern Mining; E-Learning

Conference

2008 IEEE International Conference on Systems, Man and Cybernetics, October 2008