Title: Anomaly identification of English online learning data based on local outlier factor

Authors: Yuying Liu

Addresses: Department of Basic Courses, Jiangxi Technical College of Manufacturing, Nanchang, Jiangxi, China

Abstract: In order to solve the problems of low recognition accuracy, low-recall rate and low absolute value of F1-score in traditional online English learning data anomaly identification methods, a new anomaly identification of English online learning data based on local outlier factor is proposed. English online learning data resources are utilised to be mined using K-nearest neighbours and local reachability density, and a unified data set is created by integrating data from different sources and formats. The information source model of the data set is abstracted as a tuple, and English online learning data anomaly identification is achieved by implementing the local outlier factor threshold in the tuple. The experimental results show that the proposed method has an identification accuracy of over 90%, a maximum recall rate of 98% and a high absolute F1-score, indicating good identification performance.

Keywords: local outlier factor; English online learning; data anomaly identification; K-nearest neighbours; information source model.

DOI: 10.1504/IJCAT.2023.138839

International Journal of Computer Applications in Technology, 2023 Vol.73 No.4, pp.297 - 303

Received: 14 Aug 2023
Accepted: 15 Dec 2023
Published online: 31 May 2024 *

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