Online learning resource recommendation method based on multi-similarity metric optimization under the COVID-19 epidemic

Jia Wang; Shuhao Jiang; Jincheng Ding

doi:10.1016/j.comcom.2023.04.024

Online learning resource recommendation method based on multi-similarity metric optimization under the COVID-19 epidemic

Comput Commun. 2023 Jun 1:206:152-159. doi: 10.1016/j.comcom.2023.04.024. Epub 2023 May 4.

Authors

Jia Wang¹, Shuhao Jiang^{1

2}, Jincheng Ding¹

Affiliations

¹ School of Information Engineering, Tianjin University of Commerce, Tianjin, 409 Guangrong Road, China.
² School of Electrical Automation and Information Engineering, Tianjin University, No. 92, Weijin Road, Tianjin, China.

Abstract

With the continuous COVID-19 pneumonia epidemic, online learning has become a normal choice for many learners. However, the problems of information overload and knowledge maze have been aggravated in the process of online learning. A learning resource recommendation method based on multi similarity measure optimization is proposed in this paper. We optimize the user score similarity by introducing information entropy, and use particle swarm optimization algorithm to determine the comprehensive similarity weight, and determine the nearest neighbor user with both score similarity and interest similarity through secondary screening in this method. The ultimate goal is to improve the accuracy of recommendation results, and help learners learn more effectively. We conduct experiments on public data sets. The experimental results show that the algorithm in this paper can significantly improve the recommendation accuracy on the basis of maintaining a stable recommendation coverage.

Keywords: Information entropy; Learning resource recommendation; Multi similarity; Particle swarm optimization.