Journal article 65 views
Ratings of accuracy and insight following dream interpretation by ChatGPT
Mark Blagrove,
Laura Roklicer,
Jamie Bueno,
OSCAR AUSTIN,
HARRIET FOSTER,
MEA WEBB
International Journal of Dream Research, Volume: 19, Issue: 1
Swansea University Authors: Mark Blagrove, Laura Roklicer, OSCAR AUSTIN, HARRIET FOSTER, MEA WEBB
Full text not available from this repository: check for access using links below.
Abstract
There have been many claims that ChatGPT can provide insightful interpretations of dreams. This study tests whether ChatGPT, if given a participant’s report of a recent dream, a report of their recent waking life, and their associations to the dream contents, can achieve outcome ratings by the dream...
| Published in: | International Journal of Dream Research |
|---|---|
| ISSN: | 1866-7953 |
| Published: |
Universitaet Heidelberg
2026
|
| Online Access: |
Check full text
|
| URI: | https://cronfa.swan.ac.uk/Record/cronfa71298 |
| Abstract: |
There have been many claims that ChatGPT can provide insightful interpretations of dreams. This study tests whether ChatGPT, if given a participant’s report of a recent dream, a report of their recent waking life, and their associations to the dream contents, can achieve outcome ratings by the dreamer comparable to those obtained after discussions of dreams in a lay dream group or with a therapist. The Gains from Dream Interpretation (GDI) questionnaire was used to assess participants’ evaluations of the output of ChatGPT regarding their dream. The mean GDI subscale scores were compared to subscale means from previous studies of group and therapist dream interpretations. 30 participants (mean age = 30.72 (SD=13.39)) completed this pre-registered study. Mean GDI insight-exploration subscale score was significantly lower than means for this variable in previous group and therapy studies, and each of the item scores was lower than for those previous studies. However, participants rated the ChatGPT dream interpretations as moderately accurate and as enabling some personal insight. Scores on the exploration-insight, personal insight and interpretation accuracy variables had no significant correlations with word length of the reports inputted to ChatGPT, nor with the individual difference measure Attitude Towards Dreams. As ChatGPT, other generative AI chatbots, and dedicated dream interpretation apps develop, the methods and evaluation questionnaire from the current study are available to assess the value of dream interpretations that the systems produce. This will enable comparisons between different systems and enable longitudinal assessment of individual systems across time and software version releases. |
|---|---|
| Item Description: |
https://journals.ub.uni-heidelberg.de/index.php/IJoDR/libraryFiles/downloadPublic/943 |
| Keywords: |
Dream, chatbots, ChatGPT, dream interpretation, generative AI |
| College: |
Faculty of Medicine, Health and Life Sciences |
| Issue: |
1 |