Can AI be a Poet? Comparative Analysis of Human-authored and AI-generated Poetry

Eldar Veremchuk

doi:10.4312/an.57.2.113-125

Authors

Eldar Veremchuk Zaporizhzhia National University

DOI:

https://doi.org/10.4312/an.57.2.113-125

Keywords:

authors message, Copilot, poem generation, poetry, stylistic devices

Abstract

The article deals with the problem of AI-generated poetry. It aims to investigate the difference between human-authored poems and the ones created by AI. The paper hypothesizes that AI poetic generation abilities are restricted by the algorithms, which influence its creative output. The research procedure included a gradual comparative analysis of the original human-authored poems “The Road Not Taken” by Robert Frost and “Ozymandias” by Percy Bysshe Shelley with the ones created by AI on their basis. The analysis considered seven aspects: title, structure, rhyme and rhythm, grammaticality, vocabulary, meaningfulness, imagery and poeticness. We argue that AI-generated poetic output can easier be unravelled when contrasted to the corresponding human-authored poems. We presume that the online available highlights of literary criticism (author’s message, imagery, narratives) appear to be obligatory components in the AI’s poem creation process. The obtained result can be useful for conducting further research on the generative linguistic and creative abilities of AI, their development and improvement.

Downloads

Download data is not yet available.

References

Becker, R. (1995). Dreaming at the Rexall drug. In C. B. Buckly & C. Merrill (Eds.), What will suffice: Contemporary American poets on the art of poetry (pp. 4-5). Salt Lake City, UT: Gibbs Smith.

Carr, J. M. (2003). Poetic expressions of vigilance. Qualitative Health Research, 13, 1324–1331.

Copilot. Access mode: https://www.microsoft.com/uk-ua/microsoft-copilot / retrieved June 23, 2024.

Dalen, van A. (2012). The algorithms behind the headlines: How machine-written news redefines the core skills of human journalists. Journalism Practice, 6(5–6), 648–658. doi:10.1080/17512786.2012.667268.

Elali, F. R. & Rachid, L. N. (2023). AI-generated research paper fabrication and plagiarism in the scientific community. Patterns, 4, Issue 3, 2666–3899. doi:10.1016/j.patter.2023.100706.

Faulkner, S. (2005). How do you know a good poem? Poetic re-presentation and the case for criteria. Symposium conducted at the first international conference on qualitative enquiry, 29, 95–120.

Glesne, C. (1997). That rare feeling: re-presenting research through poetic transcription. Qualitative Inquiry, 3, 202–222.

Göring, S. & Ramachandra Rao, R. R. & Merten, R. & Raake, A. (2023). Analysis of Appeal for Realistic AI-Generated Photos. IEEE Access, 11, 38999–39012. doi:10.1109/ACCESS.2023.3267968.

He, Jin. (2024). A Study on the Influence of Artificial Intelligence on Image Art Design. SHS Web of Conferences, 181. doi:10.1051/shsconf/202418104028.

Hirshfield, J. (1997). Nine gates: Entering the mind of poetry. New York: HarperCollins.

Jayanthiladevi, A. & Raj, A. & Narmadha, R. & Chandran, S. & Shaju, S. & Karani, K. P. (2020). AI in Video Analysis, Production and Streaming Delivery. Journal of Physics: Conference Series, 1712. doi:10.1088/1742-6596/1712/1/012014.

Köbis, N. & Mossink, L. D. (2021). Artificial intelligence versus Maya Angelou: Experimental evidence that people cannot differentiate AI-generated from human-written poetry. Computers in Human Behavior, 114. doi:10.1016/j.chb.2020.106553.

Langer, C. L., & Furman, R. (2004). Exploring identity and assimilation: Research and interpretive poems. Forum Qualitative Sozialforschung/Forum: Qualitative Social Research, 5(2).

Linardaki, Ch. (2022). Poetry at the first steps of Artificial Intelligence. Humanist Studies & the Digital Age, 7. doi:10.5399/uo/hsda/7.1.6.

Manurung, H. (2004). An evolutionary algorithm approach to poetry generation. Edinburgh: University of Edinburgh.

OECD (2019). AI applications. Artificial Intelligence in Society. Paris: OECD Publishing. doi:10.1787/79edf9d8-en.

Poindexter, C. C. (2002). Research as poetry: A couple experiences HIV. Qualitative Inquiry, 8, 707–714.

Rahmeh, H. (2023). Digital Verses Versus Inked Poetry: Exploring Readers’ Response to AIGenerated and Human-Authored Sonnets. Scholars International Journal of Linguistics and Literature, 372–382.

Rahwan, I. & Cebrian, M. & Obradovich, N. & Bongard, J. & Bonnefon, J.-F. & Breazeal, C. (2019). Machine behaviour. Nature, 568(7753), 477–486. doi:10.1038/ s41586-019-1138-y.

Richardson, L. (2002). Poetic representations of interviews. In J. F. Gubrium & J. A. Holstein (Eds.). Handbook of interview research: Context and method (pp. 877- 891). Thousand Oaks, CA: Sage.

Richardson, M. (1998). Poetics in the field and on the page. Qualitative Inquiry, 4, 451–462.

Samadi, V. D. & Nguyen, T. D. & Azizpour, A. & Stamm, M. C. (2024). Beyond Deepfake Images: Detecting AI-Generated Videos. Access mode: https://arxiv.org/abs/2404.15955/ retrieved June 9, 2024.

Sardinha, T. B. (2024). AI-generated vs human-authored texts: A multidimensional comparison. Applied Corpus Linguistics, 4, 2666–7991. doi:10.1016/j.acorp.2023.100083.

Sarzaeim, P. & Doshi, A. & Mahmoud, Q. (2023). A Framework for Detecting AI-Generated Text in Research Publications. Proceedings of the International Conference on Advanced Technologies. doi:10.58190/icat.2023.28.

Shalevska, Elena (2024). The Digital Laureate: Examining AI-Generated Poetry. RATE, 31. doi:10.69475/RATEI.2024.1.1.

Streitfeld, D. (2018). Computer stories: A.I. Is beginning to assist novelists. doi:10.1017/CBO9781107415324.004.

Turing, A. M. (1950). Computing machinery and intelligence. Mind - A Quarterly Review of Psychology and Philosophy, 236, 433–460.

Walsh, T. (2016). Turing’s red flag. Communications of the ACM, 59, 34–37. doi:10.1145/2838729.

Walsh, T. (2017). The meta turing test. In AAAI workshop - technical report. (pp. 132–137). California.

Yadav, N. B. & Sinha, A. & Jain, M. & Agrawal, A. & Francis, S. (2024). Generation of Images from Text Using AI. International Journal of Engineering and Manufacturing, 14, 24–37. doi:10.5815/ijem.2024.01.03.

Yao, D. (2024). Author Admits to Using AI to Write Award-winning Novel. Access mode: https://aibusiness.com/nlp/author-reveals-using-chatgpt-for-award-winning-novel/ retrieved July 5, 2024.