2023
DOI: 10.31234/osf.io/c3549
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Can AI tell good stories? Narrative Transportation and Persuasion with ChatGPT

Abstract: Storytelling is a human universal, but can Artificial Intelligence (AI) like ChatGPT tell a good story? Based on three pre-registered experiments, we investigated if narratives generated by ChatGPT or human lead to different levels of transportation, counterarguing, psychological reactance, self-referencing, and story-consistent attitudes, beliefs, and behaviors. Drawing on narratives examined in existing research, we crafted three narratives of comparable length and content using ChatGPT and labeled them alon… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2

Citation Types

0
2
0

Year Published

2023
2023
2025
2025

Publication Types

Select...
3
2
1

Relationship

0
6

Authors

Journals

citations
Cited by 11 publications
(2 citation statements)
references
References 18 publications
0
2
0
Order By: Relevance
“…Future work could take professionally-written fiction and have AI rewrite it, to provide comparison between author types (cf. Chu & Liu, 2023), or give similar prompts to human and bot writers.…”
Section: Limitationsmentioning
confidence: 99%
See 1 more Smart Citation
“…Future work could take professionally-written fiction and have AI rewrite it, to provide comparison between author types (cf. Chu & Liu, 2023), or give similar prompts to human and bot writers.…”
Section: Limitationsmentioning
confidence: 99%
“…There are other important facets of narrative reception that we did not measure, such as eudaimonia or appreciation (Oliver & Bartsch, 2010). A recent experiment tested ChatGPT narratives (vs. human) narratives in term of their narrative transportation (which has some conceptual overlap with narrative engagement), but also with key persuasive processes such as counterarguing and outcomes such as story-consistent attitudes (Chu & Liu, 2023).…”
Section: Limitationsmentioning
confidence: 99%