Dropout Rate Prediction of Massive Open Online Courses Based on Convolutional Neural Networks and Long Short-Term Memory Network

Abstract

Massive open online courses (MOOC) is characterized by large scale, openness, autonomy, and personalization, attracting increasingly students to participate in learning and gaining recognition from more and more people. This paper proposes a network model based on convolutional neural networks and long short-term memory network (CNN-LSTM) for MOOC dropout prediction task. The model selects 43-dimensional behavioral features as input from students' learning activity logs and adopts the CNN model to automatically extract continuous features over a period of time from students' learning activity logs. At the same time, considering the time sequence of students' learning behavior characteristics, a MOOC dropout prediction model was established by using long short-term memory network to obtain students' learning status at different time steps. The algorithm proposed in this chapter was trained and evaluated on the public dataset provided by the KDD Cup 2015 competition. Compared with the dropout prediction methods based on LSTM and CNN-RNN, the model improved the AUC by 2.7% and 1.4%, respectively. The result in this paper is a good predictor of dropout rates and is expected to provide teaching aid to teachers.