Effects of Parameter Improvement Mechanisms for Intelligent E-Learning Systems

In the recent years, a hot research topic in the literature is designing useful learning diagnosis systems. In order to set up effective parameters that are frequently used in the learning platforms, we advance three types of learning parameter improvement mechanisms in this article. The proposed learning parameter improvement mechanisms have three useful points: the first is that it can calculate the students´ effective online learning time; the second is that the portion of a message in discussion section which is strongly related to the learning topics can be extracted; the third is plagiarism in students´ homework can be detected easily. Then we feed the derived numeric parameters into a Support Vector Machine (SVM) classifier to predict each learner´s performance so as to verify whether they reflect the student´s studying behaviors. The results from experiments show that the prediction rate for the SVM classifier can be increased up to 35.7% in average after the inputs to the classifier are ´ ´purified´´ by the learning parameter improvement mechanisms. This great achievement reveals that the proposed algorithms indeed produce the effective learning parameters for commonly used e-learning platforms in the literature.