Векторна Модель Аналізу Стилістики Текстів

Darchuk, N.; Васильева, И В; Васильев, А. Н.

doi:10.15407/ujpe66.5.373

Ukr. J. Phys.

2021

DOI: 10.15407/ujpe66.5.373

|View full text |Cite

Векторна Модель Аналізу Стилістики Текстів

N. Darchuk

И В Васильева

А. Н. Васильев

Abstract: Стаття присвячена застосуванню фiзичних пiдходiв до аналiзу авторських стилiв українських письменникiв. Пропонується модель, у якiй лiтературнi стилi описуються векторами одиничної довжини в багатовимiрному просторi. Числовою характеристикою стилю є результат скалярного добутку вiдповiдного вектора на вектор, який визначає загальний стиль для групи авторiв. Показано, що цей параметр лiнiйним чином залежить вiд рангу автора. Така залежнiсть пiдтверджує гiпотезу приєднання до бiльшостi, вiдповiдно до якої автори… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2024

Publication Types

Select...

Article1

Relationship

Self Cite0

Independent1

Authors

Journals

Cited by 1 publication

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Stylistic Differentiation of Ukrainian-Language Texts by Parts of Speech (Experimental Linguistic and Statistical Study)

Darchuk,

Zuban

2024

BLLF

View full text Add to dashboard Cite

Вackground. The article describes an experimental linguistic and statistical study of the functional and authorial styles of the Ukrainian language, the formation of a statistical apparatus, and the application of statistical methods in establishing style-distinguishing features of Ukrainian-language media texts based on frequency dictionaries of parts of speech from the Ukrainian Language Corpus and the results of the TextAttributor 1.0 system (http://ta.mova.info). The article's authors are members of the development team of both information systems. Methods. The study used the method of modeling the stylometric structure of the text, the Student's t-test, comparative analysis of empirical data with a confidence interval for the mean square deviation, and the method of graphical representation of the stylometric model. Results. Using the automated tools of the Ukrainian Language Corpus, we calculated absolute and relative frequencies of parts of speech in Ukrainian-language texts, and the statistical behavior of parts of speech was analyzed in terms of relative frequency in functional styles (fictional prose (~ 55 million word usages); media style (~ 40 million word usages)), as well as in 8 text samples of media texts from authorial Telegram channels. The Student's t-test demonstrated that the statistical characteristics of parts of speech could serve as differential probabilities of an author's style. Additionally, the article characterizes a dynamic stylometric model implemented in the TextAttributor 1.0 system. This model attributes media texts based on 18 statistical parameters, 8 of which distinguish the part-of-speech statistical structure of the text. The obtained results indicate that the empirical statistical data of parts of speech, compared with the confidence intervals of the Ukrainian language media style, determine the individual stylistic manner of the author. Conclusions. The linguistic and statistical experiment convincingly shows that parts of speech form the statistical structure of the text, which varies depending on the functional or authorial style. The multi-parameter part-of-speech model substantiated in the study allows each examined text to determine which statistical parameters are neutral and which are differential stylometric probabilities. This model can be a benchmark for linguistic and statistical analysis of texts in other languages.

show abstract

Stylistic Differentiation of Ukrainian-Language Texts by Parts of Speech (Experimental Linguistic and Statistical Study)

Darchuk,

Zuban

2024

BLLF

View full text Add to dashboard Cite

show abstract

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.

Contact Info

customersupport@researchsolutions.com

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Made with 💙 for researchers

Part of the Research Solutions Family.

Векторна Модель Аналізу Стилістики Текстів

Cited by 1 publication

References 28 publications

Stylistic Differentiation of Ukrainian-Language Texts by Parts of Speech (Experimental Linguistic and Statistical Study)

Stylistic Differentiation of Ukrainian-Language Texts by Parts of Speech (Experimental Linguistic and Statistical Study)

Contact Info

Product

Resources

About