Bibliografia minima:IA e stili di scrittura
Questa selezione raccoglie studi, paper e articoli che raccontano come l’intelligenza artificiale impari e replichi stili di scrittura diversi. L’obiettivo è dare un quadro critico e concreto al mio esperimento: oggi, mentre le tecnologie AI entrano sempre più nelle nostre vite, non restano fuori né il giornalismo né la comunicazione politica.
Le fonti qui elencate non sono esaustive, ma organizzate in tabella per renderle semplici da consultare.
Der Kreiser
| Ambito | Autori / Anno | Titolo | Sede / Editore | Link |
|---|---|---|---|---|
| Stylization (LLM) | Bhandarkar & Wilson, 2024 | Emulating Author Style: A Feasibility Study of Prompt-enabled Text Stylization with Off-the-Shelf LLMs | ACL Anthology (Workshop on Personalization) | ACL Anthology |
| Style Transfer (autore) | Shao et al., 2024 | Authorship Style Transfer with Inverse Transfer Data Augmentation | Patterns (Cell Press) | ScienceDirect |
| Imitazione letteraria | Mikros, 2025 | Beyond the surface: stylometric analysis of GPT-4o’s capacity for literary style imitation | Digital Scholarship in the Humanities (Oxford) | Oxford Academic |
| Prompting per stile | Yang et al., 2025 | Steering Large Language Models with Register Analysis for Example-based Arbitrary Style Transfer | arXiv | arXiv |
| Riconoscimento stile LLM | Sun et al. (CMU), 2025 | Text-generating AI models have different writing styles | Futurity / CMU News | Futurity |
| Riconoscimento stile LLM | Sun et al. (CMU), 2025 | Study Shows LLMs Have Distinctive Styles (97% accuracy) | Carnegie Mellon University | CMU News |
| Propaganda persuasiva | Goldstein et al., 2024 | How persuasive is AI-generated propaganda? | PNAS Nexus (Oxford) | PNAS Nexus |
| Propaganda (policy brief) | Goldstein et al., 2024 | How Persuasive Is AI-Generated Propaganda? | Stanford HAI | PDF Stanford |
| Accademico (abstracts) | Gao et al., 2023 | Comparing scientific abstracts generated by ChatGPT to original abstracts | npj Digital Medicine (Nature) | Nature npj Digital Medicine |
| Accademico (news release) | Northwestern, 2023 | ChatGPT writes convincing fake scientific abstracts that fool reviewers | Northwestern University | Northwestern News |
| Discorsi politici | Savoy, 2024 | How good is GPT at writing political speeches for the White House? | arXiv | arXiv |
| Detection AI | Zellers et al., 2019 | Defending Against Neural Fake News | NeurIPS | arXiv |
| Detection autore | Stamatatos, 2009 | A survey of modern authorship attribution methods | JASIST (Wiley) | Wiley |