Predicting academic performance of students from VLE big data using deep learning models
作者：
Highlights：
• The data generated by the technology-enhanced learning platforms has enabled sustainable data-driven decision making.
• The clickstream data from the virtual learning environments can predict at-risk students for early intervention.
• The artificial neural network outperforms existing models in predicting students at-risk.
• The inclusion of legacy and assessment-related data improve the prediction power of the model.
摘要
•The data generated by the technology-enhanced learning platforms has enabled sustainable data-driven decision making.•The clickstream data from the virtual learning environments can predict at-risk students for early intervention.•The artificial neural network outperforms existing models in predicting students at-risk.•The inclusion of legacy and assessment-related data improve the prediction power of the model.
论文关键词：Learning analytics,Predicting success,Educational data,Machine learning,Deep learning,Virtual learning environments (VLE)
论文评审过程：Received 26 November 2018, Revised 15 October 2019, Accepted 3 November 2019, Available online 5 November 2019, Version of Record 12 November 2019.
论文官网地址：https://doi.org/10.1016/j.chb.2019.106189
