No Cover Image

Journal article 403 views 5 downloads

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, Pages: 105 - 114

Swansea University Authors: Mark Blagrove, Laura Roklicer

  • 71298.VOR.pdf

    PDF | Version of Record

    Licensed under a Creative Commons Attribution licence (CC BY 4.0).

    Download (221.12KB)

Check full text

DOI (Published version): 10.11588/ijodr.2026.1.112641

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...

Full description

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
first_indexed 2026-01-22T16:30:49Z
last_indexed 2026-05-08T06:55:39Z
id cronfa71298
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2026-05-07T13:02:49.6041424</datestamp><bib-version>v2</bib-version><id>71298</id><entry>2026-01-22</entry><title>Ratings of accuracy and insight following dream interpretation by ChatGPT</title><swanseaauthors><author><sid>8c78ee008e650b9f0a463bae56a5636c</sid><ORCID/><firstname>Mark</firstname><surname>Blagrove</surname><name>Mark Blagrove</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>a364fbe0ac4589daef513cd294acfe1a</sid><ORCID/><firstname>Laura</firstname><surname>Roklicer</surname><name>Laura Roklicer</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2026-01-22</date><abstract>There have been many claims that ChatGPT can provide insightful interpretations of dreams. This study tests whether ChatGPT, if given a participant&#x2019;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 group or with a therapist. The Gains from Dream Interpretation (GDI) questionnaire was used to assess participants&#x2019; evaluations of the output of ChatGPT regarding their dream. The mean GDI subscale scores were compared to 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 insight-exploration subscale score was significantly lower than means for this variable in previous group and therapy studies. However, ChatGPT did not differ from dream discussion groups on GDI items for thoroughness of the dream exploration, the dreamer learning what the dream means, learning how past events influence present behaviour, and the dreamer learning about their waking life issues. Participants rated the ChatGPT dream interpretations as thorough, as very or moderately accurate, and with enabling personal insight. Scores on the insight variables had no significant correlations with word length of 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 used in the current study can be used to assess the value of dream interpretations that they produce.</abstract><type>Journal Article</type><journal>International Journal of Dream Research</journal><volume>19</volume><journalNumber>1</journalNumber><paginationStart>105</paginationStart><paginationEnd>114</paginationEnd><publisher>Universitaet Heidelberg</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic>1866-7953</issnElectronic><keywords>dream, chatbot, ChatGPT, dream analysis, dream interpretation, generative AI</keywords><publishedDay>21</publishedDay><publishedMonth>4</publishedMonth><publishedYear>2026</publishedYear><publishedDate>2026-04-21</publishedDate><doi>10.11588/ijodr.2026.1.112641</doi><url/><notes/><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><apcterm>Not Required</apcterm><funders/><projectreference/><lastEdited>2026-05-07T13:02:49.6041424</lastEdited><Created>2026-01-22T16:19:45.6857956</Created><path><level id="1">Faculty of Medicine, Health and Life Sciences</level><level id="2">School of Psychology</level></path><authors><author><firstname>Mark</firstname><surname>Blagrove</surname><orcid/><order>1</order></author><author><firstname>Laura</firstname><surname>Roklicer</surname><orcid/><order>2</order></author><author><firstname>Jamie</firstname><surname>Bueno</surname><order>3</order></author><author><firstname>Oscar</firstname><surname>Austin</surname><order>4</order></author><author><firstname>Harriet</firstname><surname>Foster</surname><order>5</order></author><author><firstname>Mea</firstname><surname>Webb</surname><order>6</order></author></authors><documents><document><filename>71298__36626__d5f6e9e7891543fd9d7b9310ee650ccb.pdf</filename><originalFilename>71298.VOR.pdf</originalFilename><uploaded>2026-04-28T15:50:23.9420856</uploaded><type>Output</type><contentLength>226424</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>Licensed under a Creative Commons Attribution licence (CC BY 4.0).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2026-05-07T13:02:49.6041424 v2 71298 2026-01-22 Ratings of accuracy and insight following dream interpretation by ChatGPT 8c78ee008e650b9f0a463bae56a5636c Mark Blagrove Mark Blagrove true false a364fbe0ac4589daef513cd294acfe1a Laura Roklicer Laura Roklicer true false 2026-01-22 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 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 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 insight-exploration subscale score was significantly lower than means for this variable in previous group and therapy studies. However, ChatGPT did not differ from dream discussion groups on GDI items for thoroughness of the dream exploration, the dreamer learning what the dream means, learning how past events influence present behaviour, and the dreamer learning about their waking life issues. Participants rated the ChatGPT dream interpretations as thorough, as very or moderately accurate, and with enabling personal insight. Scores on the insight variables had no significant correlations with word length of 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 used in the current study can be used to assess the value of dream interpretations that they produce. Journal Article International Journal of Dream Research 19 1 105 114 Universitaet Heidelberg 1866-7953 dream, chatbot, ChatGPT, dream analysis, dream interpretation, generative AI 21 4 2026 2026-04-21 10.11588/ijodr.2026.1.112641 COLLEGE NANME COLLEGE CODE Swansea University Not Required 2026-05-07T13:02:49.6041424 2026-01-22T16:19:45.6857956 Faculty of Medicine, Health and Life Sciences School of Psychology Mark Blagrove 1 Laura Roklicer 2 Jamie Bueno 3 Oscar Austin 4 Harriet Foster 5 Mea Webb 6 71298__36626__d5f6e9e7891543fd9d7b9310ee650ccb.pdf 71298.VOR.pdf 2026-04-28T15:50:23.9420856 Output 226424 application/pdf Version of Record true Licensed under a Creative Commons Attribution licence (CC BY 4.0). true eng https://creativecommons.org/licenses/by/4.0/
title Ratings of accuracy and insight following dream interpretation by ChatGPT
spellingShingle Ratings of accuracy and insight following dream interpretation by ChatGPT
Mark Blagrove
Laura Roklicer
title_short Ratings of accuracy and insight following dream interpretation by ChatGPT
title_full Ratings of accuracy and insight following dream interpretation by ChatGPT
title_fullStr Ratings of accuracy and insight following dream interpretation by ChatGPT
title_full_unstemmed Ratings of accuracy and insight following dream interpretation by ChatGPT
title_sort Ratings of accuracy and insight following dream interpretation by ChatGPT
author_id_str_mv 8c78ee008e650b9f0a463bae56a5636c
a364fbe0ac4589daef513cd294acfe1a
author_id_fullname_str_mv 8c78ee008e650b9f0a463bae56a5636c_***_Mark Blagrove
a364fbe0ac4589daef513cd294acfe1a_***_Laura Roklicer
author Mark Blagrove
Laura Roklicer
author2 Mark Blagrove
Laura Roklicer
Jamie Bueno
Oscar Austin
Harriet Foster
Mea Webb
format Journal article
container_title International Journal of Dream Research
container_volume 19
container_issue 1
container_start_page 105
publishDate 2026
institution Swansea University
issn 1866-7953
doi_str_mv 10.11588/ijodr.2026.1.112641
publisher Universitaet Heidelberg
college_str Faculty of Medicine, Health and Life Sciences
hierarchytype
hierarchy_top_id facultyofmedicinehealthandlifesciences
hierarchy_top_title Faculty of Medicine, Health and Life Sciences
hierarchy_parent_id facultyofmedicinehealthandlifesciences
hierarchy_parent_title Faculty of Medicine, Health and Life Sciences
department_str School of Psychology{{{_:::_}}}Faculty of Medicine, Health and Life Sciences{{{_:::_}}}School of Psychology
document_store_str 1
active_str 0
description 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 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 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 insight-exploration subscale score was significantly lower than means for this variable in previous group and therapy studies. However, ChatGPT did not differ from dream discussion groups on GDI items for thoroughness of the dream exploration, the dreamer learning what the dream means, learning how past events influence present behaviour, and the dreamer learning about their waking life issues. Participants rated the ChatGPT dream interpretations as thorough, as very or moderately accurate, and with enabling personal insight. Scores on the insight variables had no significant correlations with word length of 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 used in the current study can be used to assess the value of dream interpretations that they produce.
published_date 2026-04-21T06:39:45Z
_version_ 1865231719856078848
score 11.106326

Similar Items