Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Currently submitted to: JMIR Formative Research

Date Submitted: Jan 8, 2026

Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.

Artificial intelligence versus human expert: An experimental test of using AI in the translation and cultural adaption of cognitive behavior therapy techniques into Arabic

  • Youstina Demetry; 
  • Per Carlbring; 
  • Gerhard Andersson

ABSTRACT

Background:

Evidence-based psychological interventions (EBPIs) are usually not accessed by marginalized groups such as refugees. Culturally adapted psychological interventions report larger effect sizes compared to non-adapted psychological interventions. A challenge, however, is the lengthy process of culturally adapting interventions.

Objective:

The aim of the current study was to investigate the acceptability and cultural relevance of two common cognitive behaviour therapy (CBT) techniques when translated and culturally adapted by artificial intelligence compared to a human expert.

Methods:

In a 2x2 factorial design, the cultural adaptation generators (AI versus human) and the CBT techniques (cognitive restructuring versus behavior modification) were compared. Raters were randomly allocated to one of four conditions. Raters were Arabic-speaking refugees and immigrants, aged between 18 to 69 years, residing in Sweden, Denmark, and Germany. CBT technique texts were rated using the cultural relevance questionnaire (CRQ) and the theoretical framework of acceptability (TFA). Two-factor between subject design analyses were used to analyze the data.

Results:

Regarding cultural relevance, a significant main effect of expert type, p = .017, η² = .045, was found in the first rating trial, with AI performing better than the human expert. No significant main effects of the CBT technique were found in the first rating, p = .10, η² = .022. There were no differences in the second trial rating. Regarding acceptability, no significant main effects of expert type, p = .087, η² = .024 or the CBT technique, p = .88, η² = .001, were found in either trial

Conclusions:

Artificial intelligence can play a role in the field of ethnopsychotherapy through acceleration of the cultural adaptation process. However, artificial intelligence still needs to be used with caution, following rigorous safety standards and robust frameworks.


 Citation

Please cite as:

Demetry Y, Carlbring P, Andersson G

Artificial intelligence versus human expert: An experimental test of using AI in the translation and cultural adaption of cognitive behavior therapy techniques into Arabic

JMIR Preprints. 08/01/2026:91056

DOI: 10.2196/preprints.91056

URL: https://preprints.jmir.org/preprint/91056

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.