Research on Constructing Online Learning Performance Prediction Model Combining Feature Selection and Neural Network

Authors

  • Huichao Mi Henan University of Economics and Law
  • Zhanghao Gao Henan University of Economics and Law
  • Qiaorong Zhang Henan University of Economics and Law
  • Yafeng Zheng Henan University of Economics and Law

DOI:

https://doi.org/10.3991/ijet.v17i07.25587

Keywords:

learning performance prediction, machine learning, logistic regression, decision tree algorithm, naive bayes, support vector machine, deep neural networks, learn-ing behavior, comparison of algorithms

Abstract


Learning performance prediction can help teachers find students who tend to fail as early as possible so as to give them timely help, which is of great significance for online education. With the availability of online data and the continuous de-velopment of machine learning technology, learning performance prediction in large-scale online education is gaining new momentum. In order to understand the performance of different machine learning algorithms in predicting multi-category learning performance in large-scale online education, this study com-pares five machine learning algorithms including logic regression, decision tree algorithm, naive Bayes, support vector machine and deep neural network. Based on 100000 data records in the edX open dataset, this study models and forecasts students' learning performance with six online learning behaviors as the eigenval-ues. In the process of modeling, missing value estimation and normalization pre-processing are carried out on the original data at first. After that, six datasets of different sizes are divided as input data. Next, the performance of the five algo-rithms is tested on data sets of different sizes. Finally, SFS, SBS and multiple re-gression analysis are used to explore the effect of behavioral feature selection on algorithm performance. The research was validated and evaluated by three met-rics: precision, recall and F1 score. The results show that the F1 score of the deep neural network with multiple regression analysis feature selection achieves 99.25% in the large-scale dataset, outperforming the related other models by 1.25%.

Author Biographies

Huichao Mi, Henan University of Economics and Law

College of Computer and Information Engineering, Henan University of Economics and Law, Zhengzhou, Henan, 45000, China

Zhanghao Gao, Henan University of Economics and Law

College of Computer and Information Engineering, Henan University of Economics and Law, Zhengzhou, Henan, 45000, China

Qiaorong Zhang, Henan University of Economics and Law

College of Computer and Information Engineering, Henan University of Economics and Law, Zhengzhou, Henan, 45000, China

Yafeng Zheng, Henan University of Economics and Law

College of Computer and Information Engineering, Henan University of Economics and Law, Zhengzhou, Henan, 45000, China

Downloads

Published

2022-04-12

How to Cite

Mi, H., Gao, Z., Zhang, Q., & Zheng, Y. (2022). Research on Constructing Online Learning Performance Prediction Model Combining Feature Selection and Neural Network. International Journal of Emerging Technologies in Learning (iJET), 17(07), pp. 94–111. https://doi.org/10.3991/ijet.v17i07.25587

Issue

Section

Papers