Model for predicting students’ academic performance in tertiary English courses

Authors

  • Liu Yang Foreign Language Department, Hebei University of Architecture, Zhangjiakou 075000, Hebei, China

Abstract

A student’s academic performance is an outcome indicating the effect of teaching and learning practices. It is important for students, teachers and school administrators that students’ academic performance be predicted accurately. Taking the learning outcome data of students enrolled in English courses at the Hebei University of Architecture in 2020 and 2021, this paper analyzed students’ English grades, taking five factors into consideration including gender and number of books borrowed, and established a particle swarm optimization-radial basis function (PSO-RBF) model for predicting students’ performance in English courses. In the proposed model, the RBF neural network in data mining was combined with PSO. It was found that the model had the best performance on data set 3, which had the largest volume of data among three distinct data sets. The PSO-RBF model had a
root-mean-square error (RMSE) value of 0.8237, a mean absolute error (MAE) value of 0.6255, and a mean absolute percentage error (MAPE) value of 0.2014, which were smaller than decision tree (DT) and k-nearest neighbor (KNN) models. The experimental results verify the reliability of the PSO-RBF model in predicting students’ academic performance in a tertiary English course, and its applicability in a real-world university setting.

Keywords: data mining, English performance, prediction model, neural network

Cite As

L. Yang, "Model for predicting students’ academic performance in tertiary English courses",
Engineering Intelligent Systems, vol. 31 no. 3, pp. 215-220, 2023.






Downloads

Published

2023-05-01

Issue

Vol. 31 No. 3 (2023): International Journal of Engineering Intelligent Systems

Section

Article

License

The submission of a paper implies that, if accepted for publication, it will not be published elsewhere in the same form, in any language, without the prior consent of the publisher. Before publication, authors are requested to assign copyright to CRL Publishing Ltd. This allows CRL to sanction photocopying, and to authorize the reprinting of issues or volumes according to demand. Authors' traditional rights will not be jeopardized by assigning Copyright in this way, as they retain the right to reuse the material following publication, and to veto third-party publication.