Title: Research on deep mining of MOOC multimodal resources based on improved Eclat algorithm

Authors: Yu Cao; Shu-Wen Chen; Yu-Xi Wang

Addresses: School of Mathematics and Information Technology, Jiangsu Second Normal University, Nanjing 210013, China ' School of Mathematics and Information Technology, Jiangsu Second Normal University, Nanjing 210013, China ' School of Mathematics and Information Technology, Jiangsu Second Normal University, Nanjing 210013, China

Abstract: In order to overcome the problems of low recall and precision in traditional MOOC multimodal resource mining methods, this paper proposes a new MOOC multimodal resource deep mining method based on improved Eclat algorithm. Based on cloud computing technology, according to MOOC resource pool structure, MOOC multi-modal knowledge map is constructed, and hash chain is used to analyse the attribute connection rules between knowledge maps. Based on the attribute connection rules, the improved Eclat algorithm is used to transform the captured modal information of resources, so as to design the MOOC multi-modal resource deep mining process and get the results of resource deep mining. The experimental results show that the recall and precision of this method are above 97%, the mining effect is better, and the mining time is always less than 0.7 s, the mining efficiency is higher, and the actual application effect is better.

Keywords: modal mining; association rules; MOOC resources; Eclat algorithm.

DOI: 10.1504/IJCEELL.2023.127871

International Journal of Continuing Engineering Education and Life-Long Learning, 2023 Vol.33 No.1, pp.99 - 113

Received: 31 Dec 2020
Accepted: 22 Mar 2021
Published online: 20 Dec 2022 *