1887
  1. Home
  2. e-Journals
  3. Journal of Language and Politics
  4. Online First Articles
  5. Online First Article
image of Could generative AI become a ghostwriter for the US president?
USD
Buy:$35.00 + Taxes

Abstract

With ChatGPT, AI generative technology has demonstrated its ability to understand user queries and to write human-like messages. Recently, other large language models (LLMs) have gained significant momentum. Based on this technology, this study analyses the style and rhetoric of three LLMs by comparing the machine-generated speeches to those of recent US presidents. Specifically, it contrasts addresses from Reagan to Biden with those produced by the GPT-3.5, GPT-4.0, and DeepSeek-v3 models. This analysis finds that LLM models frequently use the ‘we’ and produce shorter messages with, on average, longer sentences comprised of more complex words. Additionally, the computer-based models adopt a more optimistic tone and more often include terms related to political, symbolic, and abstract categories. Despite mimicking an author’s style, the generated speeches remain distinct from those of the original author. Finally, DeepSeek-v3 shows a closer similarity to those of the real US presidents.

© John Benjamins Publishing Company
Loading

Article metrics loading...

/content/journals/10.1075/jlp.24259.sav
2025-09-19
2026-07-18

  • From This Site

    /content/journals/10.1075/jlp.24259.sav
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Arnold, E., and Labbé, D.
    2015 “Vote for me. Don’t vote for the other one.” Journal of World Languages (): –. 10.1080/21698252.2015.1010250
     https://doi.org/10.1080/21698252.2015.1010250 [Google Scholar]
  2. Antoun, W., Mouilleron, V., Sagot, B., and Seddah, D.
    2023 “Towards a robust detection of language model-generated text: Is ChatGPT that easy to detect?” CORIA-TALN Conference, ParisJune 2023, –. https://aclanthology.org/2023.jeptalnrecital-long.2/
     [Google Scholar]
  3. Baayen, H. R.
    2008 “Analyzing Linguistic Data. A Practical Introduction Using R.” Cambridge University Press. 10.1017/CBO9780511801686
     https://doi.org/10.1017/CBO9780511801686
  4. Biber, D., and Conrad, S.
    2009 “Register, Genre, and Style.” Cambridge University Press. 10.1017/CBO9780511814358
     https://doi.org/10.1017/CBO9780511814358
  5. Conover, W. J.
    1990 “Practical Nonparametric Statistics.” John Wiley and Sons.
  6. Crystal, D.
    2019 “The Cambridge Encyclopedia of the English Language.” 3rd ed.Cambridge University Press.
  7. Goodfellow, I., Bengio, Y., and Courville, A.
    2016 “Deep Learning.” Boston: The MIT Press.
  8. Grimmer, J., and Stewart, B. M.
    2013 “Text as data: the promise and pitfalls of automatic content analysis methods for political texts.” Political Analysis (): –. 10.1093/pan/mps028
     https://doi.org/10.1093/pan/mps028 [Google Scholar]
  9. Guo, B., Zhang, X., Wang, Z., Jiang, M., Nie, J., Ding, Y., Yue, J., and Wu, Y.
    2023 “How close if ChatGPT to human experts? Comparison corpus, evaluation and detection.” 10.48550/arXiv.2301.07597
     https://doi.org/10.48550/arXiv.2301.07597 [Google Scholar]
  10. Harris, Z.
    1954 “Distributional structure.” Word (): –. 10.1080/00437956.1954.11659520
     https://doi.org/10.1080/00437956.1954.11659520 [Google Scholar]
  11. Hart, R. P.
    1984 “Verbal Style and the Presidency. A Computer-based Analysis.” Academic Press.
  12. Hart, R. P., Childers, J. P., and Lind, C. J.
    2013 “Political Tone. How Leaders Talk and Why.” The University of Chicago Press. 10.7208/chicago/9780226023298.001.0001
     https://doi.org/10.7208/chicago/9780226023298.001.0001
  13. Hart, R. P.
    2020 “Trump and Us. What He Says and Why People Listen.” Cambridge University Press. 10.1017/9781108854979
     https://doi.org/10.1017/9781108854979
  14. 2023 “American Eloquence: Language and Leadership in the Twentieth Century.” Columbia University Press. 10.7312/hart20906
     https://doi.org/10.7312/hart20906
  15. James, G., Witten, D., Hastie, T., and Tibshirani, R.
    2021 “An Introduction to Statistical Learning. With Applications in R.” Springer. 10.1007/978‑1‑0716‑1418‑1
     https://doi.org/10.1007/978-1-0716-1418-1
  16. Jordan, K. N., Sterling, J., Pennebaker, J. W., and Boyd, R. L.
    2019 “Examining long-term trends in politics and culture through language of political leaders and cultural institutions.” Proc. National Academy of Science (): –. 10.1073/pnas.1811987116
     https://doi.org/10.1073/pnas.1811987116 [Google Scholar]
  17. Jordan, K.
    2022 “Language analysis in political psychology.” InHandbook of Language Analysis in Psychology, edited byM. Dehghani, R. L. Boyd, –. Guilford Publications. 10.1177/0261927X13502654
     https://doi.org/10.1177/0261927X13502654 [Google Scholar]
  18. Kacewicz, E., Pennebaker, J. W., Davis, M., Jeon, M., and Graesser, A. C.
    2014 “Pronoun use reflects standings in social hierarchies.” Journal of Language and Social Psychology(): –. 10.1177/0261927X13502654
     https://doi.org/10.1177/0261927X13502654 [Google Scholar]
  19. Kreuz, R.
    2023 “Linguistics Fingerprints. How Language Creates and Reveals Identity.” Prometheus Books.
  20. Labbé, D.
    2007 “Experiments on authorship attribution by intertextual distance in English.” Journal of Quantitative Linguistics (): –. 10.1080/09296170600850601
     https://doi.org/10.1080/09296170600850601 [Google Scholar]
  21. Labbé, D., and Monière, D.
    2008 “Je est-il un autre?” Proceedings JADT, –.
     [Google Scholar]
  22. Lakoff, G., and Wehling, E.
    2012 “The Little Blue Book: The Essential Guide to Thinking and Talking Democratic.” Free Press.
  23. Markowitz, D. M.
    2023 “Analytic thinking as revealed by function words: What does language really measure?” Applied Cognitive Psychology (): –. 10.1002/acp.4057
     https://doi.org/10.1002/acp.4057 [Google Scholar]
  24. Markowitz, D. M., Kouchaki, M., Gino, F., Hancock, J. T., and Boyd, R. L.
    2023 “Authentic first impressions relate to interpersonal, social, and entrepreneurial success.” Social Psychological and Personality Science (): –. 10.1177/19485506221086138
     https://doi.org/10.1177/19485506221086138 [Google Scholar]
  25. Miller, G. A., and Charles, W. G.
    1991 “Contextual correlates of semantic similarity.” Language and Cognitive Processes (): –. 10.1080/01690969108406936
     https://doi.org/10.1080/01690969108406936 [Google Scholar]
  26. Mitrovic, S., Andreoletti, D., and Ayoub, A.
    2023 “ChatGPT or human? Detect and explain. Explaining decisions of machine learning model for detecting short ChatGPT-generated text.” 10.48550/arXiv.2301.13852
     https://doi.org/10.48550/arXiv.2301.13852 [Google Scholar]
  27. Monzani, D., Vergani, L., Pizzoli, S. F. M., Marton, G., and Pravettoni, G.
    2021 “Emotional tone, analytical thinking, and somatosensory processes of a sample of Italian tweets during the first phases of the COVID-19 pandemic: Observational study.” Journal of Medical Internet Research (). 10.2196/29820
     https://doi.org/10.2196/29820 [Google Scholar]
  28. Obradović, S., Power, S. A., and Sheehy-Skeffington, J.
    2020 “Understanding the psychological appeal of populism.” Current Opinion in Psychology ():–. 10.1016/j.copsyc.2020.06.009
     https://doi.org/10.1016/j.copsyc.2020.06.009 [Google Scholar]
  29. Ogden, C. K.
    1968 “Basic English: International Second Language.” Harcourt.
  30. Olsson, J.
    2018 “More Wordcrime. Solving Crime Through Forensic Linguistics.” Bloomsbury.
  31. Paradis, E.
    2011 “Analysis of Phylogenetics and Evolution with R.” Springer.
  32. Pennebaker, J. W.
    2011 “The Secret Life of Pronouns. What our Words Say About Us.” Bloomsbury Press.
  33. Pennebaker, J. W., Chung, C. K., Frazee, J., Lavergne, G. M., and Beaver, D. I.
    2014 “When small words foretell academic success: The case of college admissions essays.” PLoS ONE, 10.1371/journal.pone.0115844
     https://doi.org/10.1371/journal.pone.0115844 [Google Scholar]
  34. Raubach, E. E.
    2019 “Does political ideology influence how politicians speak?” Document numérique: –.
     [Google Scholar]
  35. Savoy, J.
    2018a “Analysis of the style and the rhetoric of the 2016 US presidential primaries.” Digital Scholarship in the Humanities (): –. 10.1093/llc/fqx007
     https://doi.org/10.1093/llc/fqx007 [Google Scholar]
  36. 2018b “Is Starnone really the author behind Ferrante?” Digital Scholarship in the Humanities (): –. 10.1093/llc/fqy016
     https://doi.org/10.1093/llc/fqy016 [Google Scholar]
  37. 2020 “Machine Learning Methods for Stylometry. Authorship Attribution and Author Profiling.” Springer. 10.1007/978‑3‑030‑53360‑1
     https://doi.org/10.1007/978-3-030-53360-1
  38. Savoy, J., and Wehren, M.
    2022 “Trump’s and Biden’s styles during the 2020 US presidential election.” Digital Scholarship in the Humanities (): –. 10.1093/llc/fqab046
     https://doi.org/10.1093/llc/fqab046 [Google Scholar]
  39. Sherrill, R.
    1967 “The Accidental President.” Grossman.
  40. Stamatatos, E.
    2009 “A survey of modern authorship attribution methods.” Journal of the American Society for Information Science & Technology (): –. 10.1002/asi.21001
     https://doi.org/10.1002/asi.21001 [Google Scholar]
  41. Tausczik, Y. R., and Pennebaker, J. W.
    2010 “The psychological meaning of words: LIWC and computerized text analysis methods.” Journal of Language and Social Psychology, ():–. 10.1177/0261927X09351676
     https://doi.org/10.1177/0261927X09351676 [Google Scholar]
  42. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., and Polosukhin, I.
    2017 “Attention is all you need.” InAdvances in Neural Information Processing Systems: –.
     [Google Scholar]
  43. Wolfram, S.
    2023 “What is GPT-4 Doing… and What Does it Work?” Wolfram Research Inc., Champaign.
  44. Yule, G.
    2020 “The Study of Language.” 7th ed., Cambridge University Press.
  45. Zakrzewski, C.
    2023 “ChatGPT breaks its own rules on political messages.” Washington Post, Aug 28th.
     [Google Scholar]
  46. Zhao, W., Zhou, K., Li, J., Tang, T., Wang, X., Hou, Y., Min, Y., Zhang, B., Zhang, J., Dong, Z., Du, Y., Yang, C., Chen, Y., Chen, Z., Jiang, J., Ren, R., Li, Y., Tang, X., Peiyu, P., Nie, J. Y., and Wen, J. R.
    2023 “A survey of large language models.” 10.48550/arXiv.2303.18223
     https://doi.org/10.48550/arXiv.2303.18223 [Google Scholar]
/content/journals/10.1075/jlp.24259.sav
Loading
Could generative AI become a ghostwriter for the US president?
John Benjamins ; https://doi.org/10.1075/jlp.24259.sav
/content/journals/10.1075/jlp.24259.sav
/content/journals/10.1075/jlp.24259.sav
Loading

Data & Media loading...

  • Article Type: Research Article
Keywords: large language model (LLM) ; political speeches ; DeepSeek ; stylometry ; authorship ; ChatGPT

Most Cited

This is a required field
Please enter a valid email address
Approval was successful
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error