A Novel Deep Learning Model for Student Performance Prediction Using Engagement Data

Technology-enhanced learning supported by virtual learning environments (VLEs) facilitates tutors and students.VLE platforms contain a wealth of information that can be used to mine insight regarding students’ learning behaviourand relationships between behaviour and academic performance, as well as to model data-driven decision-making.This study introduces a system that we termed ASIST: a novel Attention-aware convolutional Stacked BiLSTM net-work for student representation learning to predict their performance. ASIST exploits student academic registry, VLEclick stream, and midterm continuous assessment information for their behaviour representation learning. ASISTjointly learns the student representation using five behaviour vectors. It processes the four sequential behaviourvectors using a separate stacked bidirectional long short term memory (LSTM) network. A deep convolutional neuralnetwork models the diurnal weekly interaction behaviour. It also employs the attention mechanism to assign weightto features based on their importance. Next, five encoded feature vectors are concatenated with the assessmentinformation, and, finally, a softmax layer predicts the high-performer (H), moderate-performer (M), and at-risk (F)categories of students. We evaluate ASIST over three datasets from an Irish university, considering five evaluationmetrics. ASIST achieves an area under the curve (AUC) score of 0.86 to 0.90 over the three datasets. It outperformsthree baseline deep learning models and four traditional classification models. We also found that the attentionmechanism has a slight impact on ASIST’s performance. The ablation analysis reveals that weekly event count hasthe greatest impact on ASIST, whereas diurnal weekly interaction has the least impact. The early prediction usingthe first seven weeks of data achieves an AUC of 0.83 up to 0.89 over the three datasets. In yearly analysis, ASISTperforms best over the 2018/19 dataset and worst over the 2020/21 dataset.