University Moral Education Management System using Ensemble Learning in Data Mining

Educational data mining now serves as a powerful tool for uncovering hidden relationships within educational information and predicting students' academic achievements. However, lack of ability to learn and analyse personal data raises privacy concerns, and training data designed with biased assumptions lead to inaccurate outcomes. In this paper, the proposed Ensemble Learning (EL) techniques such as Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM) enhance accuracy in analysing the data. Pre-processing involves handling missing values by ignoring them, filling them manually, or using the attribute mean or median within the same sample. Feature selection using Information Gain selects relevant features in moral education management. Ensemble learning typically improves performance compared to individual models due to the combination of their predictions in university moral education management. Compared to existing techniques like Support Vector Machine (SVM) and Artificial Neural Networks (ANN), the proposed ensemble learning technique achieves a commendable accuracy of 94.65%, respectively.