Feature Extraction and Learning Effect Analysis for MOOCs Users Based on Data Mining

Yajuan Li


This paper aims to predict the user dropout rate in MOOC learning based on the features extracted from user learning behaviours. For this purpose, some learning behaviour features were extracted from the data of MOOC platforms. Then two machine learning algorithms, respectively based on support vector machine (SVM) and the artificial neural network (ANN), were introduced to predict the dropout rate of MOOC course. The two algorithms were contrasted with some commonly used prediction methods. The comparison results show that our algo-rithms outperformed others in the prediction of MOOC user dropout rate. The re-search sheds new light on the feature extraction and learning effect of MOOC programs.


massive open online course (MOOC); Feature extraction; Machine learning; Learning behaviour analysis

Full Text:


Copyright (c) 2018 Yajuan Li

International Journal of Emerging Technologies in Learning. ISSN: 1863-0383
Creative Commons License SPARC Europe Seal
Web of Science ESCI logo Engineering Information logo INSPEC logo DBLP logo ELSEVIER Scopus logo EDiTLib logo EBSCO logo Ulrich's logo Google Scholar logo Microsoft® Academic SearchDOAJ logo