An Intelligent Short-text Auto-marking Algorithm for Text-based Computer-mediated Communication

Abstract

In this work, an intelligent short text auto-marking algorithm for text-based computer-mediated communication is proposed. After each learner issues a short text post on the online discussion platform, a novel feature extraction approach is adopted to derive the input parameters of a one-class Support Vector Machines (SVMs) classifier. The classifier then determines if the learners' posts are related to the concept maps previously outlined by the instructor. Meanwhile, a concept map analysis approachis used to assist in determining the correctness or completeness of the learners' concept. A feedback rule construction mechanism is used to issue feedback messages to learners if necessary. The experimental results revealed that the proposed approach achieved very good diagnosis results and verified its effectiveness.