Title: A feature extraction method of English learning behaviour data based on improved maximum expectation clustering

Authors: Rui Yang

Addresses: Zhoukou Vocational and Technical College, Zhoukou, 466000, China

Abstract: Because the traditional methods do not consider the problem of data granularity control, the feature extraction accuracy of English learning behaviour data is not high, the data feature extraction results are not comprehensive and the extraction time is long. A feature extraction method of English learning behaviour data based on improved maximum expectation clustering is proposed. A data feature mining model is established, that is, adaptive mining of frequent data; control the granularity of use records of English learning activities. The improved maximum expectation clustering algorithm is used to obtain the posterior probability of the density branch of the sample to be processed to realise feature extraction. The results show that this method can effectively improve the feature extraction accuracy, the highest is about 89%, and the extraction time is less than 2.0 s.

Keywords: improved maximum expectation clustering; English learning behaviour; feature extraction; feature mining; objective function; feature mining model.

DOI: 10.1504/IJICT.2023.134254

International Journal of Information and Communication Technology, 2023 Vol.23 No.3, pp.288 - 298

Received: 04 Aug 2021
Accepted: 14 Sep 2021
Published online: 15 Oct 2023 *

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