ChatGPT as speechwriter for the French presidents

TL;DR

This study analyzes ChatGPT's writing style by comparing its generated speeches with those of French presidents, revealing stylistic differences and potential for style mimicry when given examples.

Contribution

It provides a detailed stylistic comparison between ChatGPT and presidential speeches, highlighting specific linguistic features and the model's ability to mimic style with examples.

Findings

ChatGPT overuses nouns, possessive determiners, and numbers.

ChatGPT employs fewer verbs, pronouns, and adverbs.

ChatGPT can mimic style when provided with short examples.

Abstract

Generative AI proposes several large language models (LLMs) to automatically generate a message in response to users' requests. Such scientific breakthroughs promote new writing assistants but with some fears. The main focus of this study is to analyze the written style of one LLM called ChatGPT by comparing its generated messages with those of the recent French presidents. To achieve this, we compare end-of-the-year addresses written by Chirac, Sarkozy, Hollande, and Macron with those automatically produced by ChatGPT. We found that ChatGPT tends to overuse nouns, possessive determiners, and numbers. On the other hand, the generated speeches employ less verbs, pronouns, and adverbs and include, in mean, too standardized sentences. Considering some words, one can observe that ChatGPT tends to overuse "to must" (devoir), "to continue" or the lemma "we" (nous). Moreover, GPT underuses the auxiliary verb "to be" (^etre), or the modal verbs "to will" (vouloir) or "to have to" (falloir). In addition, when a short text is provided as example to ChatGPT, the machine can generate a short message with a style closed to the original wording. Finally, we reveal that ChatGPT style exposes distinct features compared to real presidential speeches.