Comparative Analysis of Linguistic and Stylistic Characteristics of Human and Artificially Generated Media Texts

Лахно, Наталія Валентинівна та Русаченко, Наталя Павлівна та Видайчук, Тетяна Леонідівна та Петренко, Оксана та Маслова, Юлія (2026) Comparative Analysis of Linguistic and Stylistic Characteristics of Human and Artificially Generated Media Texts Lengua y Habla (31). с. 174-190. ISSN 2244-811X

Текст N_Lakhno_N_ Rusachenko_T_Vydaichuk_O_Petrenko_Y_Maslova_LH_31_FUFKM.pdf - Опублікована версія Download (774kB)

Анотація

The rapid rise of generative artificial intelligence (AI) has created a new linguistic challenge: telling apart human and machine-produced media texts. Understanding the cognitive, stylistic, and pragmatic traits of AI-generated content is crucial for evaluating its impact on communication quality and trustworthiness. This study aims to identify and describe the linguistic and stylistic features of AI-generated media texts in comparison with authentic journalistic publications. Corpus, stylometric, cognitive-pragmatic, and discursive analyses were used to assess lexical, syntactic, semantic, and rhetorical features. Results indicate that texts produced by models like ChatGPT, Gemini, and BingAI show higher grammatical accuracy, more standardized syntax, less metaphoricity, and lower emotional expressiveness than human texts. Five parameters— grammatical variability, semantic richness, pragmatic relevance, rhetorical organization, and stylistic expression—help determine the “humanness” of a text. A classification of stylistic models and linguistic markers was developed to identify text origin and measure its cognitive and communicative depth. These findings have practical applications in automatically detecting AI-authored content, enhancing digital media literacy, and setting ethical standards for AI in journalism and communication

Тип елементу :	Стаття
Ключові слова:	artificial intelligence; media discourse; linguistic analysis; stylometry;cognitive linguistics; anthropomorphism; stylistic models; generative speech; digital communication; AI-generated texts; human-like discourse; digital linguistics
Типологія:	Статті у базах даних > Scopus > У виданнях Q3 Scopus Статті у базах даних > Web of Science
Підрозділи:	Факультет української філології, культури і мистецтва > Кафедра української мови
Користувач, що депонує:	доцент Н.В. Лахно
Дата внесення:	09 Вер 2026 14:57
Останні зміни:	09 Вер 2026 14:57
URI:	https://elibrary.kubg.edu.ua/id/eprint/57573

Actions (login required)

Перегляд елементу