When Humor is Preserved or Lost: Evaluating ChatGPT and Gemini on CultureSpecific Humor Translation Strategies
Keywords:
culture-specific-humor translation, Artificial Intelligence, ChatGPT, Gemini, evaluationAbstract
Preserving humor effects that arise from flouting conversational principles in culturespecific texts presents specific difficulties when translating regional languages deeply rooted in linguistic and cultural variation. This type of humor depends on complex linguistic, cultural, and situational contexts, resulting in difficulty in replicating the same effect in the target language. This study investigates humor translation strategies and translation quality of two advanced AI language models, i.e., ChatGPT 4.0 and Gemini 2.5, in rendering culture-specific humor that deliberately violates Grice’s maxims of cooperation and Leech’s politeness principles. The study focuses on translations from Sundanese into English using 20 humorous texts selected from Cangehgar, a well-known Sundanese humor anthology characterized by deliberate violations of conversational and politeness principles. Chiaro’s four-option humor translation framework is employed to identify the strategies used, while Larson’s scales of clarity, accuracy, and naturalness are applied to evaluate translation quality. A descriptive qualitative approach is adopted, in which the selected humorous texts were purposively sampled based on their clear instances of flouting conversational and politeness principles. The findings indicate that while both models employ distinct translation strategies, their effectiveness in preserving the humor’s original intent varies. ChatGPT establishes stronger capability in maintaining the structure and essence of humor in the punchlines, whereas Gemini’s adaptations tend to dilute the comedic impact. This study contributes to the growing academic discourse on AI’s role in humor translation and its broader implications for cross-cultural communication.
References
Abu-Rayyash, H. (2024). AI meets comedy: Viewers’ reactions to GPT-4 generated humor translation. Ampersand, 12, 100162. https://doi.org/10.1016/j.amper.2023.100162
Ahammad, S. H., Kalangi, R. R., Nagendram, S., Inthiyaz, S., Priya, P. P., Faragallah, O. S., Mohammad, A., Eid, M. M. A., & Rashed, A. N. Z. (2024). Improved neural machine translation using natural language processing (NLP). Multimedia Tools and Applications, 83(13), 38579–38594. https://doi.org/10.1007/s11042-023-17207-7
Alawida, M., Mejri, S., Mehmood, A., Chikhaoui, B., & Abiodun, O. I. (2023). A comprehensive study of ChatGPT: Advancements, limitations, and ethical considerations in natural language processing and cybersecurity. Information (Switzerland), 14(8), 462. https://doi.org/10.3390/info14080462
Alnusairat, S. A., & Jaganathan, P. (2022). Humour in translation from English into Arabic: Subtitles of the comedy sitcom Friends. Theory and Practice in Language Studies, 12(7), 1402–1411. https://doi.org/10.17507/tpls.1207.27
Al-Sawaeer, S., Rabab’ah, G., & Power, A. J. (2022). Humor in the Arabic comedy show N2O. Cogent Arts & Humanities, 9(1), 2082019. https://doi.org/10.1080/23311983.2022.2082019
Anjum, A., & Lieberum, N. (2023). Exploring humor in natural language processing: A comprehensive review of JOKER tasks at CLEF Symposium 2023. In CEUR Workshop Proceedings (Vol. 3497). http://ceur-ws.org/Vol-3497
Avetisyan, H., Safikhani, P., & Broneske, D. (2023). Laughing out loud – Exploring AI-generated and human-generated humor. Computer Science and Information Technology, 13(24), 43–50. https://doi.org/10.5121/csit.2023.132406
Calvo-Ferrer, J. R. (2023). Can you tell the difference? A study of human vs. machine-translated subtitles. Perspectives: Studies in Translation Theory and Practice. https://doi.org/10.1080/0907676X.2023.2268149
Cao, Y., Zhou, L., Lee, S., Cabello, L., Chen, M., & Hershcovich, D. (2023). Assessing cross-cultural alignment between ChatGPT and human societies: An empirical study. In Proceedings of the Workshop on Cross-Cultural Considerations in NLP (C3NLP 2023) at EACL (pp. 60–71). https://doi.org/10.18653/v1/2023.c3nlp-1.7
Cennamo, I., & de Faria Pires, L. (2022). Artificial intelligence and translation: Challenges for training and the profession. Forum, 20(2), 267–282.
Chiaro, D. (2020). Humour translation in the digital age. In Humour Translation in the Age of Multimedia (pp. 17–33). Routledge. https://doi.org/10.4324/9780429316081-2
Čičak, I., & Karlić, V. (2023). Pragmatic triggers of verbal humour in Branislav Nušić’s play The Minister’s Wife. Fluminensia, 35(1), 141–160. https://doi.org/10.31820/f.35.1.8
Creswell, J. W., & Creswell, J. D. (2018). Research design: Qualitative, quantitative, and mixed methods approaches (5th ed.). SAGE Publications.
Dacosta, G. N. (2021). Strategies of flouting maxims to create humor in Friends season 5 episode 8: “The one with the Thanksgiving flashback.” Journal of Language and Literature, 21(2), 100–112.
Dore, M. (2020). Humour in audiovisual translation: Theories and applications. Routledge. https://doi.org/10.4324/9781003001928
Grice, P. (1975). Logic and conversation. In P. Cole & J. L. Morgan, Speech acts (pp. 41-58). Academic Press.
Heydon, G., & Kianbakht, S. (2020). Applying cultural linguistics to translation studies: A new model for humour translation. International Journal of Comparative Literature and Translation Studies, 8(3), 1–9. https://doi.org/10.7575/aiac.ijclts.v.8n.3p.1
Hmouri, Z. (2021). Flouting Gricean maxims for comic implicatures in Hassan El Fad’s sitcom Tendance. International Journal of Linguistics and Translation Studies, 2(2), 45–57. https://doi.org/10.36892/ijlts.v2i2.147
Jiao, W., Wang, W., Huang, J., Wang, X., & Tu, Z. (2023). Is ChatGPT a good translator? A preliminary study. arXiv Preprint. https://arxiv.org/abs/2301.08745
Kirov, V., & Malamin, B. (2022). Are translators afraid of artificial intelligence? Societies, 12(2), 46. https://doi.org/10.3390/soc12020070
Kostopoulou, L., & Misiou, V. (2023). Introduction: The transmedial turn in humour translation. In Transmedial Perspectives on Humour and Translation: From Page to Screen to Stage (pp. 1–14). Routledge. https://doi.org/10.4324/9781003317104-1
Krisdwiyani, I., & Hanidar, S. (2022). The production of conversational humor by flouting Gricean maxims in the sitcom The IT Crowd. Lexicon, 9(1), 1–14. https://doi.org/10.22146/lexicon.v9i1.72803
Larson, M. L. (1998). Meaning-based translation: A guide to cross-language equivalence (2nd ed.). University Press of America.
Leech, G. (1983). Principles of pragmatics. Longman. https://doi.org/10.4324/9781315835976
Li, J., Wu, X., Liu, X., Xie, Q., Tiwari, P., & Wang, B. (2023). Can language models make fun? A case study in Chinese comical crosstalk. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (pp. 7542–7558). https://doi.org/10.18653/v1/2023.acl-long.419
Luiz, T. M. (2020). Humor translation in theater. Cadernos de Tradução, 40(1), 91–107. https://doi.org/10.5007/2175-7968.2020v40n1p91
Meng, H. (2022). The application of puns in English advertisements and translation strategy analysis. Advances in Education, Humanities and Social Science Research, 1(2), 174–182. https://doi.org/10.56028/aehssr.1.2.174
Mondal, S. K., Zhang, H., Kabir, H. M. D., Ni, K., & Dai, H. N. (2023). Machine translation and its evaluation: A study. Artificial Intelligence Review, 56(9), 8713–8738. https://doi.org/10.1007/s10462-023-10423-5
Pichal, S., & Hassabis, D. (2024). Introducing Gemini 1.5: Google’s next-generation AI model. Google DeepMind. https://deepmind.google/discover/blog/introducing-gemini-1-5-googles-next-generation-ai-model
Pilyarchuk, K. (2023). Humour and allusions on screen: Looking into translation strategies of The Simpsons. European Journal of Humour Research, 11(2), 1–15. https://doi.org/10.7592/EJHR2023.11.2.787
Qing, L. (2022). On the strategies of machine translation post-editing based on cloud platform. Advances in Engineering Technology Research, 3(1), 11–18. https://doi.org/10.56028/aetr.3.1.11
Rane, N. (2024). Role and challenges of ChatGPT, Gemini, and similar generative artificial intelligence in human resource management. Studies in Economics and Business Relations, 5(1), 25–39. https://doi.org/10.48185/sebr.v5i1.1001
Raphaelson-West, D. S. (2012). On the feasibility and strategies of translating humour. Meta: Journal des Traducteurs, 34(1), 128–141. https://doi.org/10.7202/003913ar
Sahari, Y., Al-Kadi, A. M. T., & Ali, J. K. M. (2023). A cross-sectional study of ChatGPT in translation: Magnitude of use, attitudes, and uncertainties. Journal of Psycholinguistic Research, 52(6), 1523–1536. https://doi.org/10.1007/s10936-023-10031-y
Xia, C., Amini, M., & Lee, K. F. (2023). Humor translation: A case study on the loss of humorous loads in SpongeBob SquarePants. Cadernos de Tradução, 43(1), 1–18. https://doi.org/10.5007/2175-7968.2023.e89705
Yulianti, K., & Handayani, N. D. (2022). The humor formed by flouting the maxim in Hawkeye TV series. Humanitatis: Journal of Language and Literature, 8(2), 157–167. https://doi.org/10.30812/humanitatis.v8i2.1675
Yustika, L. S., Setiawan, S., & Retnaningdyah, P. (2022). Flouting maxim in The Hundred-Foot Journey movie: An opportunity to improve students’ intercultural literacy. Journal of Pragmatics Research, 4(2), 137–151. https://doi.org/10.18326/jopr.v4i2.137-151
Zuo, B. (2020). Why does humor fail or occur unexpectedly? An account of humor within an extended relevance theory. Journal of Pragmatics, 160, 37–47. https://doi.org/10.1016/j.pragma.2020.02.006
Published
Issue
Section
Copyright (c) 2025 Alan Jaelani, Ratna Dewanti
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
