Deep Learning-Based Method for Predicting Student Dropouts in MOOCs

Massive Open Online Courses (MOOCs) have attracted a large number of students due to their unique teaching methods and high-quality course resources. However, the high dropout rates present a significant challenge, affecting the sustainable development of MOOC platforms and diminishing students' learning effectiveness. To address this issue, this paper proposes a deep learning-based model to predict student dropout behavior. The experimental data is sourced from the MOOCCube2020 dataset. Initially, a convolutional neural network (CNN) is used to extract implicit features from temporal feature data, which are then input into a bidirectional long short-term memory (BiLSTM) network. Subsequently, a fusion attention mechanism recalculates(ATT) the hidden layer states output by the BiLSTM layer. The final result is obtained through continuous training and optimization. Experimental results demonstrate that the model effectively captures the correlation between learning behaviors and dropout behaviors, enabling accurate predictions of student dropouts.