Telling Jokes Like a Human? Humour and Irony in AI-Generated Discourse

This study examines the construction of humour and irony in artificial intelligence-generated discourse, with particular focus on outputs produced by OpenAI ChatGPT and Google Google Bard. Drawing upon Incongruity Theory and discourse-pragmatic approaches, the research investigates how large language models simulate humorous interaction through linguistic patterning while lacking the contextual and sociocultural inferencing associated with human humour. The dataset consists of 200 AI-generated jokes and ironic statements produced through structured prompting strategies across multiple humour categories, including puns, sarcasm, hyperbole, and observational humour. Corpus-assisted analysis was employed to identify recurring linguistic markers, pragmatic strategies, and humour failure patterns within the dataset. The findings indicate that AI systems demonstrate considerable competence in generating surface-level humour structures, particularly formulaic setup-punchline sequences and lexical wordplay. However, the models encounter substantial limitations when humour relies on implicature, contextual sensitivity, cultural knowledge, or emotional nuance. Several recurrent humour failures were identified, including inadvertent literalism, cultural decontextualisation, semantic incoherence, and formal repetitiveness. Comparative observations with human-generated humour further suggest that AI discourse remains constrained by probabilistic language modelling rather than genuine pragmatic understanding. The study contributes to emerging scholarship on AI-mediated discourse by demonstrating the distinction between structural humour replication and deeper communicative competence. It also raises broader implications concerning the use of humour-capable AI systems in digital communication, entertainment, content production, and human-machine interaction.

AI discourse, humour, irony, language models, pragmatics

1. Attardo, S. (2020a). Humor in interaction. Cambridge University Press. [Google Scholar] [Crossref]

2. Attardo, S. (2020b). Irony and sarcasm. In S. Attardo (Ed.), Humor 2.0: How the Internet changed funny forever (pp. 43–62). Springer. [Google Scholar] [Crossref]

3. Dynel, M. (2021). Irony, deception and humour: An interdisciplinary perspective. Journal of Pragmatics, 171, 59–72. [Google Scholar] [Crossref]

4. Fiske, A., Henningsen, P., & Buyx, A. (2021). Your robot therapist will see you now: Ethical implications of embodied artificial intelligence in mental health care. Journal of Medical Ethics, 47(9), 614–615. [Google Scholar] [Crossref]

5. Floridi, L., & Chiriatti, M. (2020). GPT-3: Its nature, scope, limits, and consequences. Minds and Machines, 30(4), 681–694. [Google Scholar] [Crossref]

6. Gatt, A., & Paggio, P. (2021). Multimodal humour: Exploring the boundaries of computational creativity. Frontiers in Artificial Intelligence, 4, 703731. [Google Scholar] [Crossref]

7. Grice, H. P. (2021). Logic and conversation. In S. Davis (Ed.), Pragmatics: A reader (pp. 305–315). Routledge. (Original work published 1975) [Google Scholar] [Crossref]

8. Gros, L., Kaminski, M. E., & Umbrello, S. (2023). Algorithmic psychotherapists: The ethics of using conversational AI in mental health. AI and Ethics, 3, 115–132. [Google Scholar] [Crossref]

9. Hempelmann, C. F., & Ruch, W. (2021). Robots and humour: Does an artificial intelligence have a sense of humor? Humor: International Journal of Humor Research, 34(3), 307–331. [Google Scholar] [Crossref]

10. Holmes, J. (2019). Humour and the construction of identity. In J. Culpeper, M. Haugh, & D. Z. Kádár (Eds.), The Palgrave handbook of linguistic (im)politeness (pp. 359–382). Palgrave Macmillan. [Google Scholar] [Crossref]

11. Nijssen, D., & Heylen, K. (2021). How funny are GPT-3’s jokes? An analysis of humor in language models. Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis, 1–10. [Google Scholar] [Crossref]

12. Rashkin, H., Choi, E., Jang, J. Y., Volkova, S., & Choi, Y. (2019). Towards empathetic open-domain conversation models: A new benchmark and dataset. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 5370–5381. [Google Scholar] [Crossref]

13. Ritchie, G. (2020). The linguistic analysis of jokes. Routledge. [Google Scholar] [Crossref]

14. Shah, C., Bhatia, A., & Kaur, A. (2021). Automatic joke generation: Learning humor from examples. arXiv Preprint. [Google Scholar] [Crossref]

15. West, R., Djuric, N., & Poon, H. (2022). Evaluating AI humor: Human ratings and machine judgments. Findings of the Association for Computational Linguistics (ACL), 1641–1650. [Google Scholar] [Crossref]