CoChat

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

Petrenko, Oksana, Maslova, Yuliia, Lakhno, Nataliia, Rusachenko, Natalia, Vydaichuk, Tetiana · 2026 · LENGUA Y HABLA
Cited by 1

The DOI matches its DataCite record; 1 of the 1 references it cites were found in a registry or an index.

Abstract

The rapid rise of generative artificial intelligence (AI) has created a new linguistic challenge: distinguishing human from machine-produced media texts. Understanding the cognitive, stylistic, and pragmatic characteristics of AI-generated content is crucial for evaluating its impact on communication quality and reliability. This study aims to identify and characterize linguistic and stylistic features of AI-generated media texts compared to authentic journalistic publications. Corpus, stylometric, cognitive-pragmatic, and discursive analyses were employed to assess lexical, syntactic, semantic, and rhetorical dimensions. Results indicate that texts produced by models such as ChatGPT, Gemini, and BingAI exhibit higher grammatical accuracy, standardized syntax, reduced metaphoricity, and lower emotional expressiveness than human texts. Five parameters—grammatical variability, semantic richness, pragmatic relevance, rhetorical organization, and stylistic expression—determine the “humanness” of a text. A classification of stylistic models and linguistic markers was developed to identify text origin and evaluate its cognitive and communicative depth. The findings have practical applications for automated detection of AI authorship, enhancing digital media literacy, and establishing ethical standards for AI use in journalism and communication.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

DataCite · 10.5281/zenodo.19441249

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 1 references

Cited by

See all 1

Metadata

Authors
Petrenko, O., Maslova, Y., Lakhno, N., Rusachenko, N., & Vydaichuk, T.
Affiliations
  • PhD, Candidate of Philological Sciences, Associate Professor, Department of Linguistics and Translation, Faculty of Foreign Languages, Yuriy Fedkovych Chernivtsi National University, Chernivtsi, Ukraine
  • PhD in Philology, Associate Professor, Department of Information and Document Communications, Educational and Scientific Institute of International Relations and National Security, National University of Ostroh Academy, Ostroh, Ukraine
  • PhD in Linguistics, Associate Professor, Department of Ukrainian Language, Faculty of Ukrainian Philology, Culture and Art, Borys Grinchenko Kyiv Metropolitan University, Kyiv, Ukraine
Venue
LENGUA Y HABLA
Publisher
LENGUA Y HABLA
Published
2026-03-20
References
1

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Comparative Analysis of Linguistic and Stylistic Characteristics of Human and Artificially Generated Media Texts. https://app.cochat.ai/papers/10.5281/zenodo.19441249
The paper
Petrenko, O., Maslova, Y., Lakhno, N., Rusachenko, N., & Vydaichuk, T. (2026). Comparative Analysis of Linguistic and Stylistic Characteristics of Human and Artificially Generated Media Texts. LENGUA Y HABLA. https://doi.org/10.5281/zenodo.19441249

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.