Title: A recognition method of learning behaviour in English online classroom based on feature data mining

Authors: Lu Shi; Xiaoran Di

Addresses: School of Foreign Languages, Xi'an Aeronautical University, Xi'an, 710077, China ' School of Foreign Languages, Xi'an Aeronautical University, Xi'an, 710077, China

Abstract: This paper proposes a recognition method of learning behaviour in English online classroom based on feature data mining. Firstly, with the support of fractal theory, the adjacent search method is used to extract the edge of learning behaviour image, and then the data clustering method is used to reduce the dynamic change range of data caused by edge extraction and improve the degree of data standardisation. Finally, the optimal characteristics of learning behaviour are obtained by Drosophila optimisation algorithm, then the learning behaviour recognition of English online classroom is realised by mining characteristic data. Simulation results show that this method has the highest accuracy of 98% and the comprehensiveness of recognition of different types of learning behaviour can reach 0.95. This method retains the details of behaviour image as much as possible to make it more practical.

Keywords: feature data mining; behaviour identification; proximity search method; fruit fly optimisation algorithm; data clustering.

DOI: 10.1504/IJRIS.2023.128375

International Journal of Reasoning-based Intelligent Systems, 2023 Vol.15 No.1, pp.8 - 14

Received: 27 Dec 2021
Accepted: 13 Apr 2022
Published online: 18 Jan 2023 *