Analysis on Course Scores of Learners of Online Teaching Platforms Based on Data Mining
Nan Zhou, Zhaofeng Zhang, Jing Li
Abstract
After years of development, online teaching platforms (OLPs) have accumulated a huge amount of data on student scores. To effectively mine out the useful knowledge and information behind the massive data, this paper puts forward a course score analysis model for OLP learners based on data mining. Firstly, the score features of OLP learners were classified, and the calculation method of computational features was presented. Then, the score features were clustered through expectation maximization (EM) clustering, which has the advantage of unsupervised learning. Moreover, the salient features were obtained through principal component analysis (PCA). Finally, the support vector machine (SVM) prediction algorithm, a supervised learning method, was constructed, and merged with the clustering algorithm to realize accurate classification of the course scores of OLP learners. The effectiveness of the proposed method was proved through experiments. Based on the correlation between learner scores and courses, this research enables teachers to improve current teaching models and methods.