Conference Paper/Proceeding/Abstract 391 views
Assessment of exploration-insight gains following ‘discussion’ of a dream using ChatGPT
Mark Blagrove,
Laura Roklicer,
Jamie Bueno,
Oscar Austin,
Harriet Foster,
Mea Webb
International Journal of Dream Research, Volume: 18, Issue: Supplement 1, Start page: S24
Swansea University Author: Mark Blagrove
Full text not available from this repository: check for access using links below.
Abstract
Edwards et al. (2013, 2015) showed that the Ullman technique of discussing dreams leads to similar scores on the exploration-insight subscale of the Gains from Dream Interpretation (GDI) questionnaire as occurs for exploration of dreams with a therapist. The Ullman technique uses a relatively atheor...
| Published in: | International Journal of Dream Research |
|---|---|
| ISSN: | 1866-7953 |
| Published: |
University of Heidelburg: Heidelburger-OJS Journals
2025
|
| Online Access: |
Check full text
|
| URI: | https://cronfa.swan.ac.uk/Record/cronfa70021 |
| Abstract: |
Edwards et al. (2013, 2015) showed that the Ullman technique of discussing dreams leads to similar scores on the exploration-insight subscale of the Gains from Dream Interpretation (GDI) questionnaire as occurs for exploration of dreams with a therapist. The Ullman technique uses a relatively atheoretical mapping of dream content onto recent waking life. The current study aims to test whether ChatGPT, if given a participant’s dream report, a report of their recent waking life, and free associations to the dream, can emulate an Ullman discussion of a recent dream. The Gains from Dream Interpretation questionnaire was used to assess participants’ evaluations of the ‘discussion’ output of ChatGPT regarding their dream. 24 participants completed the study (Males, n = 5; females, n = 19; mean age = 31.39). Mean insight-exploration subscale score = 6.73 (SD=1.47), which is significantly lower than means for this variable in studies by Edwards et al., Blagrove et al., and Hill. Personal insight subscale score of 6.03 (SD=1.75) did not differ significantly from the mean score of 6.60 (SD=1.43) in Edwards et al. (2015). The item ‘Overall, how accurate do you find the ChatGPT interpretation of your dream?’, with responses rated from 1 = extremely inaccurate to 9 = extremely accurate, had mean score = 7.33 (SD=1.14). Participants thus saw the ChatGPT dream interpretation as very or moderately accurate, with personal insight occurring, but with exploration of the dream being less thorough and involving than in group discussions. Edwards, C., Malinowski, J., McGee, S., Bennett, P., Ruby, P. & Blagrove, M. (2015). Comparing personal insight gains due to consideration of a recent dream and consideration of a recent event using the Ullman and Schredl dream group methods. Frontiers in Psychology 6, 831. Edwards, C. Ruby, P. Malinowski, J. Bennett, P. & Blagrove, M. (2013). Dreaming and insight. Frontiers in Psychology, 4(979) doi:10.3389/fpsyg.2013.00979 |
|---|---|
| Item Description: |
Abstract |
| Keywords: |
dream; dream interpretation; ChatGPT; generative AI |
| College: |
Faculty of Medicine, Health and Life Sciences |
| Issue: |
Supplement 1 |
| Start Page: |
S24 |