Out-Heroding Herod? — Author-trained GPTs and Original Works in the Perspective of Quantitative Linguistics

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61988987%3A17250%2F25%3AA2603D2P" target="_blank" >RIV/61988987:17250/25:A2603D2P - isvavai.cz</a>

Výsledek na webu

<a href="https://ojs.cuni.cz/pedagogika/article/view/4945" target="_blank" >https://ojs.cuni.cz/pedagogika/article/view/4945</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.14712/23362189.2025.4945" target="_blank" >10.14712/23362189.2025.4945</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Out-Heroding Herod? — Author-trained GPTs and Original Works in the Perspective of Quantitative Linguistics

Popis výsledku v původním jazyce

Goals: The paper compares texts created by GPT models trained on the works of prominent Czech authors and the pieces of literature they actually wrote. The goal is to find out (1) whether there are any differences between the two; and if so, (2) in what sphere of language these differences are the most prominent.Methods: The authors used for building GPTs are Karel Čapek, Jaroslav Hašek, Franz Kafka, and Vladislav Vančura. The corpus contains 40 1,000-word text samples per each, 20 of them produced by the respective GPT and 20 taken from the original works. Two investigations are carried out – the first includes calculating 30 morphological, syntactic, and lexical markers for each text; the second  is based on most-frequent-element analyses. The results of the first set are tested on statistical significance via Mann–Whitney U Test.Results: The chatbots do not reflect colloquiality of style and conversation interaction very well, and tend to make texts more narrative. The best results are obtained for Karel Čapek, the worst for Franz Kafka. The stylometric analyses almost always distinguish the AI- and human-generated pieces of language.Conclusions: The texts produced by the author-trained GPTs are still very well distinguishable from those produced by real writers.

Název v anglickém jazyce

Out-Heroding Herod? — Author-trained GPTs and Original Works in the Perspective of Quantitative Linguistics

Popis výsledku anglicky

Goals: The paper compares texts created by GPT models trained on the works of prominent Czech authors and the pieces of literature they actually wrote. The goal is to find out (1) whether there are any differences between the two; and if so, (2) in what sphere of language these differences are the most prominent.Methods: The authors used for building GPTs are Karel Čapek, Jaroslav Hašek, Franz Kafka, and Vladislav Vančura. The corpus contains 40 1,000-word text samples per each, 20 of them produced by the respective GPT and 20 taken from the original works. Two investigations are carried out – the first includes calculating 30 morphological, syntactic, and lexical markers for each text; the second  is based on most-frequent-element analyses. The results of the first set are tested on statistical significance via Mann–Whitney U Test.Results: The chatbots do not reflect colloquiality of style and conversation interaction very well, and tend to make texts more narrative. The best results are obtained for Karel Čapek, the worst for Franz Kafka. The stylometric analyses almost always distinguish the AI- and human-generated pieces of language.Conclusions: The texts produced by the author-trained GPTs are still very well distinguishable from those produced by real writers.

Druh

J_ost - Ostatní články v recenzovaných periodicích

CEP obor

—

OECD FORD obor

60203 - Linguistics

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Pedagogika

ISSN

0031-3815

e-ISSN

2336-2189

Svazek periodika

—

Číslo periodika v rámci svazku

4

Stát vydavatele periodika

CZ - Česká republika

Počet stran výsledku

25

Strana od-do

355-379

Kód UT WoS článku

—

EID výsledku v databázi Scopus

—