Title: Bayesian network algorithms used in the assessment of learners' learning behaviour

Authors: Suzhen Li

Addresses: Weifang University of Science and Technology, Shandong Shouguang 262700, China

Abstract: In order to solve the problem that teachers cannot monitor learners' learning behaviour or evaluate learners' learning objectively and scientifically because of the relative separation of time and space between teachers and students, covering Bayesian network learning evaluation model based on knowledge relationship is proposed. The information related to students can be divided into two parts: domain-related information and domain-independent information. Firstly, the modelling of domain-related information is mainly discussed. The process of domain-related information modelling is the Bayesian networking process of the courses that students have learned. Secondly, the time and space complexity of the algorithm is reduced by simplifying the network structure and optimising the order of node deletion in the triangulation process. The results show that the model can accurately judge the degree of students' mastery of knowledge, and can provide students with personalised guidance strategy.

Keywords: network learning; learning evaluation; Bayesian network; student model.

DOI: 10.1504/IJCEELL.2021.116032

International Journal of Continuing Engineering Education and Life-Long Learning, 2021 Vol.31 No.3, pp.360 - 370

Received: 09 Jun 2019
Accepted: 12 Oct 2019

Published online: 27 Apr 2021 *

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