Title: Personalised recommendation of mobile learning materials based on hierarchical hidden Markov models

Authors: Zhaofeng Li; Ping Hu; Yuchuan Hu; Yan Zhang

Addresses: School of Software, Henan Institute of Science and Technology, Xinxiang, Henan Province, 453003, China ' School of Software, Henan Institute of Science and Technology, Xinxiang, Henan Province, 453003, China ' School of Software, Henan Institute of Science and Technology, Xinxiang, Henan Province, 453003, China ' School of Software, Henan Institute of Science and Technology, Xinxiang, Henan Province, 453003, China

Abstract: The research on personalised recommendation of mobile learning materials can meet learners' learning needs, thus further improving their learning efficiency and effectiveness. In order to solve the problems of low accuracy, low recall and low user satisfaction in traditional personalised recommendation methods for mobile learning materials, a personalised recommendation method of mobile learning materials based on hierarchical hidden Markov model is proposed. K-means clustering algorithm is used to mine the data of mobile learning platform, and user portraits of mobile learning platform are extracted according to the data mining results and user interest feature vectors. According to the user portrait and hierarchical hidden Markov model, the top-N recommendation list is generated to realise personalised recommendation of mobile learning materials. The experimental results show that the maximum accuracy of personalised recommendation of mobile learning materials is 97.3%, the maximum recall rate is 97.9%, and the average satisfaction rate is 98.1.

Keywords: hierarchical hidden Markov model; mobile learning materials; personalised recommendation; K-means clustering algorithm; user portrait.

DOI: 10.1504/IJCEELL.2025.146017

International Journal of Continuing Engineering Education and Life-Long Learning, 2025 Vol.35 No.3/4, pp.297 - 311

Received: 19 Apr 2024
Accepted: 06 Nov 2024
Published online: 01 May 2025 *

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