Applications of Data Mining to an Asynchronous Argumentation Based Learning Assistance Platform

Abstract

Structured argumentation support environments have been built and used in scientific discourse in the literature. These environments emphasized either on exchanging information or on constructing arguments for presentation. In this work, an intelligent online asynchronous argumentation platform that detects whether the learners address the expected discussion issues is proposed. After each learner issues an argument on the learning platform, a term weighting method is adopted to derive inputs parameters of a SVM classifier. The classifier then determines if the learners' arguments are related to the concept maps outlined by the instructor. Notably, a peer review mechanism is established in this work to improve the quality of term weighting approach. The experimental results revealed that the students in a junior high school participating in argumentation learning activities of natural science were benefited by the proposed argumentation based learning assistance platform.