Title: Research on bilingual text similarity detection and analysis based on improved fragment merging algorithm

Authors: Miao Zhang

Addresses: Liberal Arts Business School, Xi'an Siyuan University, Xi'an City, Shaanxi Province, 710000, China

Abstract: To achieve cross language text similarity analysis, an improved fragment merging algorithm based on dynamic programming is proposed. Dynamic programming is introduced into the fragment merging algorithm to improve the merging algorithm, so as to improve the cross language detection, gradually merge fragments from keyword detection, and verify the performance of the algorithm, such as recall, accuracy and detection time, through comparative analysis experiments. The results show that the recall and accuracy of the merging algorithm based on dynamic programming are more than 80% in the performance test. In addition, it can be found that the fragment merging algorithm has faster fragment merging speed and plagiarism detection speed in the comparison of algorithms. The performance of the improved fragment merging algorithm in plagiarism detection has great advantages, but also has great application value, which provides a new solution for the field of text similarity calculation.

Keywords: cross language; similarity analysis; dynamic programming; plagiarism detection; fragment merging.

DOI: 10.1504/IJCSM.2023.133635

International Journal of Computing Science and Mathematics, 2023 Vol.18 No.2, pp.189 - 202

Received: 13 Apr 2022
Accepted: 10 Feb 2023
Published online: 26 Sep 2023 *

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