JOURNAL ARTICLE
Can AI tell good stories? Narrative transportation and persuasion with ChatGPT.
Published In: Journal of Communication, 2024, v. 74, n. 5. P. 347 1 of 3
Database: Academic Search Ultimate 2 of 3
Authored By: Chu, Haoran; Liu, Sixiao 3 of 3
Abstract
This article investigates the ability of OpenAI's ChatGPT, an AI language model powered by GPT-4, to generate engaging and persuasive narratives compared to human-created stories used in social science research and interventions. Across three pre-registered experiments, findings show that while ChatGPT-generated narratives often matched human narratives in transportation (audience immersion) and persuasive effects, they generally elicited lower counterarguing (audience skepticism) than human-authored stories. However, labeling narratives as AI-generated consistently reduced transportation and increased counterarguing, indicating public skepticism toward AI authorship regardless of actual content quality. The study highlights ChatGPT's strengths in linguistic competence and logical coherence but notes limitations in creativity and lived experience, which may affect narrative vibrancy and emotional engagement. These results suggest potential applications of AI in narrative persuasion while cautioning against risks of misinformation and emphasizing the need for interdisciplinary research on AI storytelling.
Additional Information
- Source:Journal of Communication. 2024/10, Vol. 74, Issue 5, p347
- Document Type:Article
- Subject Area:Literature and Writing
- Publication Date:2024
- ISSN:0021-9916
- DOI:10.1093/joc/jqae029
- Accession Number:180861362
- Copyright Statement:Copyright of Journal of Communication is the property of Oxford University Press / USA and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Looking to go deeper into this topic? Look for more articles on EBSCOhost.