Title: Automatic classification of multi-source and multi-granularity teaching resources based on random forest algorithm

Authors: Dahui Li; Peng Qu; Tao Jin; Changchun Chen; Yunfei Bai

Addresses: School of Computer and Control Engineering, Qiqihar University, Qiqihar, Heilongjiang, 161006, China ' School of Computer and Control Engineering, Qiqihar University, Qiqihar, Heilongjiang, 161006, China ' School of Computer and Control Engineering, Qiqihar University, Qiqihar, Heilongjiang, 161006, China ' School of Computer and Control Engineering, Qiqihar University, Qiqihar, Heilongjiang, 161006, China ' School of Computer and Control Engineering, Qiqihar University, Qiqihar, Heilongjiang, 161006, China

Abstract: In traditional teaching resource classification methods, the classification accuracy is low and the RDV value of classification convergence is high. Through fuzzy information mining and fusion clustering method, multi-source and multi-granularity teaching resource data is obtained. With the help of incremental orthogonal component analysis method, the dimension of multi-source and multi-granularity teaching resource data is reduced. First, the teaching resource data is brought into random forest. Then, the filtering error of teaching resource is determined according to the classification parameter nonlinear feature recognition results. Finally, the multi-source and multi-granularity teaching resource classification is completed. The experimental results show that the highest classification accuracy is about 98%, and the lowest RDV is about 0.015.

Keywords: random forest algorithm; multi-source; multi-granularity; teaching resources; automatic; automatic classification.

DOI: 10.1504/IJCEELL.2023.129236

International Journal of Continuing Engineering Education and Life-Long Learning, 2023 Vol.33 No.2/3, pp.177 - 191

Received: 04 Feb 2021
Accepted: 13 May 2021

Published online: 01 Mar 2023 *

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