Визначення здатності штучного інтелекту до встановлення авторства художнього україномовного тексту за значними фрагментами
Loading...
Date
2023
Journal Title
Journal ISSN
Volume Title
Publisher
Український державний університет науки і технологій, ННІ ≪Інститут промислових та бізнес технологій≫, ІВК ≪Системні технології≫, Дніпро
Abstract
UKR: Штучний інтелект стає невід’ємною частиною побутового життя та професійної діяльності людини. Представлена робота має на меті дослідити ефективність визначення авторства художніх текстів за допомогою сучасних інструментів штучного інтелекту, а саме інтелектуальна пошукова система Bing. Для експерименту було вибрано десять українських авторів з багатим доробком художніх творів, які відображають різні аспекти української культури та історії. Випадкові фрагменти довжиною до 500 слів були вибрані з різних творів цих авторів. Було проведено експеримент з визначення авторства 360 фрагментів. Використовуючи мову програмування Python та пакет skpy, було створено програмне забезпечення, яке надсилає запити та отримує відповіді від Bing бота, вбудованого в Microsoft Skype. В текстах відповідей перевірялася наявність імені автора фрази та відповідної назви твору. Встановлено, що довгі фрагменти дозволяють з високою точністю, але не завжди визначити автора художнього україномовного тексту.
ENG: Artificial intelligence is becoming an integral part of everyday life and professional activity of a person. Bing, as an intelligent search system, can serve as a tool for determining the authorship of artistic text in Ukrainian. Bing helps to uncover in-formation about a text fragment and its author, although the search results may be inaccurate or incomplete. This work aims to explore the effectiveness of determining the authorship of artistic texts using modern artificial intelligence tools based on significant fragments of works. Ten Ukrainian authors with a rich body of artistic works, reflecting various aspects of Ukrainian culture and history, were selected for the experiment. Random fragments up to 500 words in length were selected from various works of these authors. An experiment was conducted to determine the authorship of 360 fragments. Using the Python programming language and the skpy package, software was created that sends queries and receives responses from the Bing bot embedded in Microsoft Skype. The presence of the author’s name and the corresponding title of the work were checked in the response texts. This work introduces, for the first time, a method of verifying the authorship of Ukrainian-language text fragments using the Bing bot equipped with artificial intelligence. A comparative analysis was conducted and experiments were carried out to identify the authorship of significant long fragments. It was found that long fragments allow the author of the artistic Ukrainian text to be determined with high accuracy. Ivan Franko has the highest percentage of responses where the author’s name and the title of the work were mentioned - 87%. The proposed hypothesis regarding the effectiveness of artificial intelligence in establishing authorship of works has not been confirmed. Artificial intelligence has slightly lower efficiency than expected, which indirectly exposes its means of operation. Namely, when establishing authorship, a sequential research comparison of the proposed fragment with a bank of works that are widespread in the Internet environment is not performed.
ENG: Artificial intelligence is becoming an integral part of everyday life and professional activity of a person. Bing, as an intelligent search system, can serve as a tool for determining the authorship of artistic text in Ukrainian. Bing helps to uncover in-formation about a text fragment and its author, although the search results may be inaccurate or incomplete. This work aims to explore the effectiveness of determining the authorship of artistic texts using modern artificial intelligence tools based on significant fragments of works. Ten Ukrainian authors with a rich body of artistic works, reflecting various aspects of Ukrainian culture and history, were selected for the experiment. Random fragments up to 500 words in length were selected from various works of these authors. An experiment was conducted to determine the authorship of 360 fragments. Using the Python programming language and the skpy package, software was created that sends queries and receives responses from the Bing bot embedded in Microsoft Skype. The presence of the author’s name and the corresponding title of the work were checked in the response texts. This work introduces, for the first time, a method of verifying the authorship of Ukrainian-language text fragments using the Bing bot equipped with artificial intelligence. A comparative analysis was conducted and experiments were carried out to identify the authorship of significant long fragments. It was found that long fragments allow the author of the artistic Ukrainian text to be determined with high accuracy. Ivan Franko has the highest percentage of responses where the author’s name and the title of the work were mentioned - 87%. The proposed hypothesis regarding the effectiveness of artificial intelligence in establishing authorship of works has not been confirmed. Artificial intelligence has slightly lower efficiency than expected, which indirectly exposes its means of operation. Namely, when establishing authorship, a sequential research comparison of the proposed fragment with a bank of works that are widespread in the Internet environment is not performed.
Description
О. Іванов: ORCID 0000-0003-1259-6377; В. Скалозуб: ORCID 0000-0002-1941-4751; В. Горячкін: ORCID 0000-0002-8952-952X; В. Шинкаренко: ORCID 0000-0001-8738-7225
Keywords
визначення авторства, природомовний текст, штучний інтелект, генеративні мовні моделі, ChatGPT, бот Bing, Skype, definition of authorship, natural language text, artificial intelligence, generative language models, Bing bot, КІТ
Citation
Іванов О. П., Скалозуб В. В., Горячкін В. М., Шинкаренко В. І. Визначення здатності штучного інтелекту до встановлення авторства художнього україномовного тексту за значними фрагментами. Системні технології. Дніпро, 2023. Т. 5, № 148. С. 86–98. DOI: 10.34185/1562-9945-5-148-2023-08.