Mining learner profile utilizing association rule for common learning misconception diagnosis

Abstract

With the rapid growth of computer and Internet technologies, e-learning has become a major trend in the computer assisted teaching and learning fields. Most past researches for Web-based learning commonly neglect to consider whether learners can understand the learning courseware or generate misconception. To discover common learning misconception of learners, this study employs the association rule to mine learner profile for diagnosing learners' common learning misconception during learning processes. In this paper, the association rules that occurring misconception A implies occurring misconception B can be discovered utilizing the proposed association rule learning diagnosis approach. Meanwhile, the obtained association rules for the common learning misconception are applied to tune courseware structure as well as perform remedy learning. Experiment results indicate that applying the proposed learning diagnosis approach can correctly discover learners' common learning misconception according to learner profile and help learners to learn more effectively.