In this article we will discuss the work of a semantic comparison method, through which the detection of plagiarism is revealed in the fuzzy information, which we have designed an algorithm with a semantic dimension to detect plagiarism in the fuzzy information and detect impersonations such as changing the structure of speech or replacing words with synonyms and limiting technical spelling errors such as not completely writing the end of the word or unofficial and unknown abbreviations, and analyze shows the degree of similarity of the original text, and analyzes the overall evaluation of the degree of similarity of texts from the apparent structures of the text. Experiments have shown that the proposed method with a semantic dimension in the case of fuzzy information is better than sherlock method in terms of file size criterion of 6% if using word synonyms in the file and 1% in case of rewriting the file. As for the standard time taken to examine the files through the acceleration calculation, it is noted that the proposed method for the semantic dimension in the case of fuzzy information is faster in performance than the Sherlock method in the case of the use of synonyms 1.02 times and in the case of rewriting words with a value of 1.01 times in the case of file size 382 words. The results of the experiments show that the average execution time of the proposed algorithm, for finding plagiarism, is less by 3.47% compared with the Sherlock algorithm in the case of the use of synonyms and less by 1.83% compared with the Sherlock algorithm in the case of rewriting words. The algorithm works effectively as the file size increases, the gain ratio is obtained up to 2.73% in the synonym of words and 2.69% in the case of rewriting words. From the results presented in the tables, we conclude that the average error rate of the proposed algorithm is 2% lower than the error rate sherlock algorithm. The complexity of the proposed algorithm is O(m*n).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.