Title: Personalised recommendation method for MOOC online educational resources: collaborative filtering algorithm

Authors: Min Fan

Addresses: Hangzhou Vocational Technical College, Hangzhou, 310018, China

Abstract: In order to address the practical challenges associated with the low recall rate, accuracy, and user satisfaction in conventional personalised recommendation approaches for educational materials, a personalised recommendation method for MOOC online educational resources based on collaborative filtering algorithm is proposed. The mean shift clustering algorithm is used for clustering processing of MOOC platform data, and the MFA algorithm is used to dimensionality reduction process the clustering results. Learner interest are determined by considering the label preference based on frequency weight, time weight, comprehensive frequency and time, as well as learners' interest preferences for label clusters. Based on the analysis of learner interest, personalised recommendation of MOOC online education resources is achieved using a collaborative filtering algorithm based on semi-supervised learning. Experimental results show that the maximum recall rate of this method is 98.3%, the maximum recommendation accuracy is 97.8%, the mean learner satisfaction is 97.95, indicating good recommendation effectiveness.

Keywords: collaborative filtering algorithm; MOOC; online educational resources; personalised recommendation; semi-supervised learning.

DOI: 10.1504/IJCEELL.2025.143803

International Journal of Continuing Engineering Education and Life-Long Learning, 2025 Vol.35 No.1/2, pp.156 - 170

Received: 12 Mar 2024
Accepted: 09 Sep 2024
Published online: 07 Jan 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article