On Analysis and Modeling of Student Browsing Behavior in Web-Based Asynchronous Learning Environments

Abstract

Recently, the rapid progress of Internet technology stirs the widespread development of web-based learning environments in the educational world. As compared with conventional CAI systems, web-based learning environments are able to accumulate a huge amount of learning data. As a result, there is an urgent need for analyzing methods of discovering useful information from the huge log database for improving instructional effectiveness. In this paper, we focus on analyzing the historical browsing data to reconstruct a browsing model that enables teachers to identify some interesting or unexpected browsing patterns in student’s learning process, and therefore might provide knowledge for teachers to reorganize their web structure for effectiveness. For this purpose, we had developed an analysis tool based on data mining technique. The constructed browsing model includes a set of document clusters and sequence rules among those clusters. Finally, an application of the analysis is conducted on a real database collected from three web-based courses in Ming Chuan University, Taiwan. Through this case study, we investigate the effectiveness of the analysis tool, and some revelations are presented and discussed.