A Comparative Study of Generative AIs’ Capabilities for Metaphor Analysis: A Case Study of Fire Metaphors in English Online Discourse
Article Sidebar
Main Article Content
Abstract
Recent advancements in generative AI technology have increased the role of AI in academic research. However, the capability of different generative AIs in analyzing metaphors has not been adequately investigated. The purpose of this paper is to compare the capability of ChatGPT, Gemini, and DeepSeek in analyzing fire metaphors in online discourse. Data were based on the iWeb Corpus, and 100 concordance lines of three verbs that potentially instantiated fire metaphors, namely, “spark,” “fuel,” and “dampen,” were collected for analysis by the human researcher. The data were then analyzed by each of the generative AIs. The analyses were compared against those of the researcher. Cohen’s Kappa was used to determine the intercoder agreement. The analysis reveals 14 target domains associated with the fire metaphors. The results indicate that there is substantial agreement between the researcher and each of the generative AIs. However, a closer look at the analysis of individual words reveals variation from moderate to almost perfect agreement, with DeepSeek scoring the highest. The implications of the roles of AI in metaphor research are discussed.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
Bowen, N. E. J. A., & Watson Todd, R. (2025). Enhancing ChatGPT-based writing research through effective prompt use. Teaching English with Technology, 25(1), 26–40.
Charteris-Black, J. (2017). Fire metaphors: Discourses of awe and authority. Bloomsbury.
Charteris-Black, J. (2021). Metaphors of the pandemic: Fire and force of nature. In J. Charteris-Black (Ed.), Metaphors of Coronavirus: Invisible enemy or zombie apocalypse? (pp. 61–91). Palgrave Macmillan. https://doi.org/10.1007/978-3-030-85106-4_3
Crosthwaite, P., & Baisa, V. (2023). Generative AI and the end of corpus-assisted data-driven learning? Not so fast! Applied Corpus Linguistics, 3(3), 1–4. https://doi.org/10.1016/j.acorp.2023.100066
Curry, N., Baker, P., & Brookes, G. (2024). Generative AI for corpus approaches to discourse studies: A critical evaluation of ChatGPT. Applied Corpus Linguistics, 4(1), 1–9. https://doi.org/10.1016/j.acorp.2023.100082
Dahiru, S., & Saidu, A. (2018). Metaphorical conceptualizations of ANGER in English and Fulfulde. European Journal of Literature, Language and Linguistic Studies, 2(2), 9–21. https://doi.org/10.5281/zenodo.1203355
Davies, M. (2020). The Corpus of Contemporary American English (COCA). http://corpus.byu.edu/coca/
Deignan, A. (2005). Metaphor and corpus linguistics (Vol. 6). John Benjamins Publishing.
Diep, N. L. (2023). Conceptual metaphor “Media is Fire”. Proceedings of the AsiaCall International Conference, 4, 63–74.
Geng, H., & Nimehchisalem, V. (2023). Can ChatGPT analyse textual data? The sub-themes reflected by typical conceptual metaphors in short stories of language assessment. ASEAN Journal of Applied Linguistics, 2(December), 16–31.
Gewirt, D. (2025). The top 20 AI tools of 2025 - and the #1 thing to remember when you use them. ZD Net. https://www.zdnet.com/article/the-top-20-ai-tools-of-2025-and-the-1-thing-to-remember-when-youuse-them/
Guenier, A. W., Wang, B., Li, M., & Xing, M. (2025). How metaphors facilitate intercultural health communication: Insights from traditional Chinese medicine doctors in UK clinics. Journal of World Languages, 11(2), 319–342. https://doi.org/10.1515/jwl-2025-0025
Hardie, A., Koller, V., Rayson, P., & Semino, E. (2008). Exploiting a semantic annotation tool for metaphor analysis. Metaphorike.De, 15, 141–160. http://comp.eprints.lancs.ac.uk/1527/1/49_Paper.pdf
Hart, C. (2018). ‘Riots engulfed the city’: An experimental study investigating the legitimating effects of fire metaphors in discourses of disorder. Discourse and Society, 29(3), 279–298. https://doi.org/10.1177/0957926517734663
Hesse, J. (2023). Machines and metaphors: Challenges for the detection, interpretation and production of metaphors by computer programs. Theoria (Sweden), 89(5), 607–624. https://doi.org/10.1111/theo.12481
Hunston, S. (2002). Corpora in applied linguistics. Cambridge University Press.
Ichien, N., Stamenković, D., & Holyoak, K. J. (2023). Large language model displays emergent ability to interpret novel literary metaphors. Metaphor and Symbol, 39(4), 296–309. https://doi.org/10.1080/10926488.2024.2380348
Kheovichai, B. (2025). A corpus-based analysis of eating metaphors in American English from the perspective of conceptual metaphor and lexical priming theories. LEARN Journal: Language Education and Acquisition Research Network, 18(1), 1–22.
Kovaliuk, Y. (2024). Connecting idioms and metaphors: Where cognitive linguistics meets cognitive stylistics. B.A.S. British and American Studies, 30, 157–170. https://doi.org/10.35923/BAS.30.15
Kovecses, Z. (2010). Metaphor: A practical introduction (2nd ed.). Oxford University Press. https://doi.org/10.1023/A:1023919116538
Lakoff, G. (1990). Women, fire and dangerous things. Chicago University Press.
Landis, J. R., & Koch, G. G. (1977). The measurement of observer agreement for categorical data. Biometrics, 33(1), 159–174. https://doi.org/10.2307/2529310
Liu, Y., & Li, D. (2026). Metaphors and China’s COVID-19 policies: A diachronic analysis of Chinese-English bilingual news editorials. Text & Talk. 46 (1), 53–78. https://doi.org/10.1515/text-2024-0068
Davies, M., & Kim, J.-B. (2019). The advantages and challenges of “big data”: Insights from the 14 billion word iWeb corpus. Linguistic Research, 36(1), 1–34. https://doi.org/10.17250/khisli.36.1.201903.001
Pragglejaz Group. (2007). MIP: A method for identifying metaphorically used words in discourse. Metaphor and Symbol, 22(1), 1–39. https://doi.org/10.1207/s15327868ms2201_1
Reijnierse, W. G. (2018). DMIP: A method for identifying potentially deliberate metaphor in language use. Corpus Pragmatics, 2(2), 129–147. https://doi.org/10.1007/s41701-017-0026-7
Sengar, S. S., Hasan, A. Bin, Kumar, S., & Carroll, F. (2024). Generative artificial intelligence: A systematic review and applications. Multimedia Tools and Applications. 84, 23661–23700. https://doi.org/10.1007/s11042-024-20016-1
Stefanowitsch, A. (2006). Words and their metaphor: A corpus-based approach. In A. Stefanowitsch & S. Gries (Eds.), Corpus-based approaches to metaphor and metonymy (pp. 64–105). Mouton de Gruyter.
Tao, R., Kim, S. J., Lu, L., Kang, J., & McLeod, D. (2023). Fighting fire or fighting war: Examining the framing effects of COVID-19 metaphors. Health Communication, 39(10), 2026–2040. https://doi.org/10.1080/10410236.2023.2253398
Yang, C., Chen, P., & Huang, Q. (2024). Can ChatGPT’s performance be improved on verb metaphor detection tasks? Bootstrapping and combining tacit knowledge. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, 1, 1016–1027. https://aclanthology.org/2024.acl-long.57
