RUS  ENG
Full version
JOURNALS // Informatsionnye Tekhnologii i Vychslitel'nye Sistemy // Archive

Informatsionnye Tekhnologii i Vychslitel'nye Sistemy, 2024 Issue 2, Pages 74–85 (Mi itvs859)

INTELLIGENT SYSTEMS AND TECHNOLOGIES

Some features of literary texts when comparing them to determine their authorship

G. N. Akhobadze, E. Yu. Rusyaeva

V. A. Trapeznikov Institute of Control Sciences of Russian Academy of Sciences, Moscow, Russia

Abstract: A method for analyzing literary author's texts based on selecting the most frequent auxiliary parts of speech characteristic of a particular author's style and calculating their weighting coefficients has been developed. This linguistic analysis of natural language text (NLP) is based on the calculation of the most frequently used prepositions, conjunctions and particles in literary works. The process of calculating weight coefficients, determined by the ratio of the values of auxiliary parts of speech in the text to its total volume, has been analyzed in detail. Experimental results on establishing the authorship of literary texts for two authors are presented. The results were obtained by comparing the numerical values of the same type of weighting coefficients, expressed as percentages. The theoretical and practical results obtained can be used to analyze, identify linguistic features, and differences not only in literary texts, but, in the future, in texts of any genre and style.

Keywords: weight coefficient, auxiliary part of speech, authorship, text, identity indicator, repeatability.

DOI: 10.14357/20718632240207



Bibliographic databases:


© Steklov Math. Inst. of RAS, 2026