Enhanced CNN Models for Binary and Multiclass Student Classification on Temporal Educational Data at the Program Level

Abstract

In educational data mining, student classification is an important and popular task by predicting final study status of each student. In the existing works, this task has been considered in many various contexts at both course and program levels with different learning approaches.However, its realworld characteristics such as temporal aspects, data imbalance, data overlapping, and data shortage with sparseness have not yet been fully investigated. Making the most of deep learning, our work is the first one addressing those challengesfor the program-level student classification task. In a simple but effective manner, convolutional neural networks (CNNs) are proposed to exploit their wellknown advantages on images for temporal educational data. As a result, the task is resolved by our enhanced CNN models with more effectiveness and practicability on real datasets. Our CNN models outperform other traditional models and their various variants on a consistent basis for program-level student classification.

Prediction of Student Academic Performance Using a Hybrid 2D CNN Model

“…Bashir et al employed a hybrid deep neural network to calculate student academic performance by combining bidirectional LSTM (BLSTM) with an attention layer that emphasizes important features from the contextual information received by the BLSTM layer [74]. Chau et al employed a two-dimensional CNN to classify temporal education data and predict student labels with three different class labels: graduation, study stop, and studying [75]. Chau et al employed transformation to build a matrix of features from temporal data, which was then fed into the picture's color channel to convert the 1D data to a 2D image; employed a single 2D CNN architecture for classification; and compared the results to typical machine learning models.…”