ARTIFICIAL INTELLIGENCE AND HUMAN INTERPRETATION IN LITERARY ANALYSIS: THE LIMITS OF AUTOMATED UNDERSTANDING OF METAPHOR, CONTEXT AND NARRATIVE NUANCE
Abstract
This article examines the role of artificial intelligence in literary analysis, with particular attention to the limits of automated interpretation in relation to metaphor, context and narrative nuance. Modern AI systems can process large volumes of literary data, identify lexical patterns, classify emotional tone and support structural analysis. However, literary interpretation requires more than pattern recognition. It involves cultural memory, historical awareness, aesthetic sensitivity, ambiguity, irony and the reader’s subjective experience. The article follows the IMRAD structure and analyses AI as an auxiliary instrument rather than an autonomous interpreter. The study argues that artificial intelligence may significantly enhance philological research by accelerating technical procedures and revealing hidden textual regularities, but it cannot fully replace human hermeneutic judgement. The most productive model is therefore a hybrid approach in which computational tools support, but do not dominate, human literary interpretation.
Keywords
artificial intelligence, literary analysis, metaphor, narrative nuance, context, interpretation, computational philology, digital humanities, human understanding.How to Cite
References
Bamman, D., Underwood, T., & Smith, N. A. (2014). A Bayesian mixed effects model of literary character. Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, 370–379. https://doi.org/10.3115/v1/P14-1035
Bender, E. M., & Koller, A. (2020). Climbing towards NLU: On meaning, form, and understanding in the age of data. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 5185–5198. https://doi.org/10.18653/v1/2020.acl-main.463
Chan, C. K. Y. (2025). Assessing the ability of generative AI in English literary analysis. Information Retrieval Journal. https://doi.org/10.1007/s10791-025-09572-8
Hatzel, H. O., Biemann, C., & Jannidis, F. (2023). Machine learning in computational literary studies. it – Information Technology, 65(4–5), 195–207. https://doi.org/10.1515/itit-2023-0041
Ichien, N., Stamenković, D., & Holyoak, K. J. (2024). Large language model displays emergent ability to interpret novel literary metaphors. Metaphor and Symbol, 39(4), 253–271. https://doi.org/10.1080/10926488.2024.2380348
Jannidis, F., Konle, L., & Leinen, P. (2025). Do large language models understand literature? Journal of Computational Literary Studies, 4(1), 1–26.
Kommers, C. (2025). Evaluating generative AI as a cultural technology. Computational Culture.
Moretti, F. (2013). Distant reading. Verso.
Underwood, T. (2019). Distant horizons: Digital evidence and literary change. University of Chicago Press.
Yakura, H., Yamada, M., & Shimizu, K. (2024). Evaluating large language models’ ability using a test of nuanced human communication. Journal of Intelligence, 12(7), 70. https://doi.org/10.3390/jintelligence12070070.
License
Copyright (c) 2026 Diyora Sultanboyeva , Diana Valerevna Abduramanova
This work is licensed under a Creative Commons Attribution 4.0 International License.
