GENERATIVE ARTIFICIAL INTELLIGENCE IN THE STUDY OF TYPOGRAPHICAL INNOVATIONS IN CONTEMPORARY ENGLISH-LANGUAGE LITERARY NARRATIVE

Keywords: generative artificial intelligence, English-language literary narrative, typographical innovations, typographical devices, linguistic and stylistic analysis, digital humanities, literary text

Abstract

The article explores the potential of using generative artificial intelligence in the analysis of typographical innovations in contemporary English-language literary narrative. The relevance of the study is determined by the rapid development of generative language models and their increasing integration into contemporary humanities and linguistic research, opening new opportunities for the comprehensive analysis of literary texts. Particular attention is paid to typographical innovations as an essential component of an author’s stylistic system, performing not only graphical but also meaning-making, expressive, pragmatic, and compositional functions within the structure of contemporary English-language literary narrative. The study characterizes the principal typographical innovations found in contemporary English-language literary narrative, including the use of italics, capitalization, font variation, graphic text segmentation, unconventional spatial arrangement of textual elements, the combination of diverse typographical techniques, and other means of visual organization of literary discourse. The potential of generative artificial intelligence for the automated identification, systematization, classification, and interpretation of typographical features in accordance with the contextual framework of literary works is analysed. The findings demonstrate that the application of generative artificial intelligence facilitates the rapid processing of extensive textual corpora, enhances the efficiency of preliminary linguistic and stylistic analysis, and enables the identification of patterns in the functioning of typographical devices across literary narratives of different genres. At the same time, the study establishes that the results generated by artificial intelligence require critical scholarly interpretation, as current language models are not always capable of fully accounting for the cultural, historical, pragmatic, and individual authorial contexts of literary works. It is argued that the most effective approach involves combining traditional philological methods with the analytical capabilities of generative artificial intelligence, thereby providing a more comprehensive understanding of the functional potential of typographical innovations in contemporary Englishlanguage literary narrative. The scientific novelty of the research lies in the comprehensive examination of generative artificial intelligence as a tool for analysing typographical innovations in English-language literary narrative and in identifying its capabilities and limitations within contemporary linguistic research.

References

1. Atwood M. The Handmaid’s Tale. London: Jonathan Cape, 1985. 324 p.
2. Bender E. M., Gebru T., McMillan-Major A., Shmitchell S. On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency (FAccT). New York: ACM, 2021. P. 610–623. DOI: 10.1145/3442188.3445922.
3. Bommasani R., Hudson D. A., Adeli E. et al. On the Opportunities and Risks of Foundation Models. Stanford: Stanford University, 2021. 252 p.
4. Brown D. The Da Vinci Code. New York : Doubleday, 2003. 597 p.
5. Danielewski M. Z. House of Leaves. New York: Pantheon Books, 2000. 709 p.
6. Drucker J. Graphesis: Visual Forms of Knowledge Production. Cambridge, MA: Harvard University Press, 2014. 200 p.
7. Foer J. S. Extremely Loud & Incredibly Close. Boston: Houghton Mifflin, 2005. 368 p.
8. Ishiguro K. Never Let Me Go. London: Faber & Faber, 2005. 288 p.
9. Jurafsky D., Martin J. H. Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition. 3rd ed. Draft. Stanford University, 2024.
10. King S. The Shining. New York: Doubleday, 1977. 447 p.
11. Kress G., van Leeuwen T. Reading Images: The Grammar of Visual Design. 3rd ed. London: Routledge, 2021. 312 p.
12. Manning C. D. Human Language Understanding & Reasoning. Daedalus. 2022. Vol. 151, № 2. P. 127–138.
13. Nørgaard N. Multimodal Stylistics of the Novel: More Than Words. London: Routledge, 2019. 232 p.
14. OpenAI. GPT-4 Technical Report. PDF version. URL: https://cdn.openai.com/papers/gpt-4.pdf (дата звернення: 04.08.2026).
15. Meta AI. Llama 2: Open Foundation and Fine-Tuned Chat Models. URL: https://ai.meta.com/llama/ (дата звернення: 04.08.2026).
16. Stanford Center for Research on Foundation Models. On the Opportunities and Risks of Foundation Models. URL: https://crfm.stanford.edu/report.html (дата звернення: 04.08.2026).
17. Stanford University. Speech and Language Processing (3rd ed.). URL: https://web.stanford.edu/~jurafsky/slp3/ (дата звернення: 04.08.2026).
18. Touvron H., Martin L., Stone K. Et al. Llama 2: Open Foundation and Fine-Tuned Chat Models. 2023. URL: https://arxiv.org/abs/2307.09288
Published
2026-11-18
How to Cite
Yukhymets, S. Y. (2026). GENERATIVE ARTIFICIAL INTELLIGENCE IN THE STUDY OF TYPOGRAPHICAL INNOVATIONS IN CONTEMPORARY ENGLISH-LANGUAGE LITERARY NARRATIVE. New Philology, (103), 269-277. https://doi.org/10.26661/2414-1135-2026-103-33
Section
Articles