Stylistic Differentiation of Ukrainian-Language Texts by Parts of Speech (Experimental Linguistic and Statistical Study)
Bibliographic Data
| ID | 21780193 |
|---|---|
| Authors | Nataliia Darchuk (0000-0001-8932-9301), Oksana Zuban (0000-0002-2644-3892) |
| Year | 2024 |
| Issue | 36 |
| Pages | 47-56 |
| Publication date | 2024-01-01 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Bulletin of Taras Shevchenko National University of Kyiv Literary Studies Linguistics Folklore Studies (JOURNAL) |
| Journal identifiers | ISSN: 1728-2659 • E-ISSN: 2709-8494 |
| Publisher | Taras Shevchenko National University of Kyiv (PUBLISHER • UA) |
| DOI | 10.17721/1728-2659.2024.36.08 |
| OpenAlex | W4404068152 |
| Language | EN |
| References cited | 8 |
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
Linguistics · Ukrainian · Computer Science · Discourse Analysis and Cultural Communication · Linguistics, Language Diversity, and Identity · Literature, Language, and Rhetoric Studies · Philosophy · Psychology
| Highly cited | No |
|---|