CONSTRUCTIVE MODELING APPLICATION IN THE TEXTS AUTHORSHIP DETERMINING
DOI:
https://doi.org/10.34185/1991-7848.itmm.2023.01.103Keywords:
natural language texts, authorship determination, statistical analysis, classification, correlation coefficient, constructive-production modelingAbstract
The development of the constructor, which allows displaying the sentences construction peculiarities for different authors, is presented. This approach takes into account the sentences structure characteristic of an individual author and can be used to detect plagiarism and establish the authorship of texts in various genres and styles. Thanks to which, the usual paraphrasing of the work or changing the order of sections, sentences or words will not become an obstacle for authorship determining. The proposed approach is promising and low-cost in terms of calculation capacity, unlike the existing ones. This way of the sentences construction representation is presented for the very first.
References
Foltýnek, Tomáš & Meuschke, Norman & Gipp, Bela. Academic Plagiarism Detection: A Systematic Literature Review. ACM Computing Surveys. 52. 2019. 1-42. 10.1145/3345317.
Ahuja, Lovepreet & Gupta, Vishal & Kumar, Rohit. A New Hybrid Technique for Detection of Plagiarism from Text Documents. Arabian Journal for Science and Engineering. 2020. 45. 1-14. 10.1007/s13369-020-04565-9.
V. I. Shynkarenko, V. M. Ilman. Constructive-Synthesizing Structures and Their Grammatical Interpretations. I. Generalized Formal Constructive-Synthesizing Structure / Cybernetics and Systems Analysis, 2014, Volume 50, Issue 5, pp 8-16.
V. I. Shynkarenko, I. M. Demidovich. Natural Language Texts Authorship Establishing Based on the Sentences Structure, in: Proceedings of the 6th International Conference on Computational Linguistics and Intelligent Systems (COLINS 2022), Volume I: Main Conference, Gliwice, Poland, May 22-23, 2022, pp. 328-337.
