Assessing the use of ChatGPT as a psychoeducational tool for mental health practice
The DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Abstract
Background: Psychoeducation is an important part of mental health services offered by counsellors. This study used qualitative content analysis to explore ChatGPT, a generative artificial intelligence (AI) tool, as a resource for psychoeducation in the context of mental health. Method: Researchers created carefully crafted prompts based on common psychoeducational themes provided to clients, covering seven critical areas: depression, anxiety, general health, substance abuse, religious/spiritual issues, lifestyle, routine health habits and interpersonal matters. A coding manual was developed encompassing six criteria to assess the quality of psychoeducational responses of ChatGPT: accuracy, clarity, relevance, empathy, engagement and ethical considerations. Findings: The reviewers assessed ChatGPT's responses to 21 psychoeducational prompts as accurate, clear and relevant, with an empathic tone in responses to emotionally challenging queries. ChatGPT engages users by offering actionable steps and suggestions. The tool consistently demonstrated ethical considerations by advising users to consult qualified professionals when necessary. The findings suggested ChatGPT's potential as a reliable source of psychoeducation, particularly for individuals with very limited access to mental health resources. Conclusion: This research underscores ChatGPT's potential as a valuable psychoeducational resource for mental health concerns while emphasising the need for ongoing assessment and user feedback to address its limitations and ensure responsible practice in the dynamic field of AI‐powered mental health support. Future studies should explore user experiences and incorporate diverse perspectives to further enhance our understanding of ChatGPT's utility in real‐world mental health contexts.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Qualitative Content Analysis in Practice
Schreier, M. (2012) · doi:10.4135/9781529682571 · Cited by 5,801
Qualitative Content Analysis: A Focus on Trustworthiness
Elo, S., Kääriäinen, M., Kanste, O., Pölkki, T., Utriainen, K., & Kyngäs, H. (2014) · Sage Open · doi:10.1177/2158244014522633 · Cited by 4,395
Prevalence of mental disorders in China: a cross-sectional epidemiological study
Huang, Y., Wang, Y., Wang, H., Liu, Z., Yu, X., Yan, J., Yu, Y., Kou, C., Xu, X., Lu, J., et al. (2019) · The Lancet Psychiatry · doi:10.1016/s2215-0366(18)30511-x · Cited by 2,335
ChatGPT: five priorities for research
van Dis, E. A. M., Bollen, J., Zuidema, W., van Rooij, R., & Bockting, C. L. (2023) · Nature · doi:10.1038/d41586-023-00288-7 · Cited by 1,842
DeCuir-Gunby, J. T., Marshall, P. L., & McCulloch, A. W. (2011) · Field Methods · doi:10.1177/1525822x10388468 · Cited by 1,456
Sagar, R., Dandona, R., Gururaj, G., Dhaliwal, R. S., Singh, A., Ferrari, A., Dua, T., Ganguli, A., Varghese, M., Chakma, J. K., et al. (2020) · The Lancet Psychiatry · doi:10.1016/s2215-0366(19)30475-4 · Cited by 886
Algorithmic bias in data-driven innovation in the age of AI
Akter, S., McCarthy, G., Sajib, S., Michael, K., Dwivedi, Y. K., D’Ambra, J., & Shen, K. N. (2021) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2021.102387 · Cited by 440
ChatGPT and consumers: Benefits, Pitfalls and Future Research Agenda
Paul, J., Ueno, A., & Dennis, C. (2023) · International Journal of Consumer Studies · doi:10.1111/ijcs.12928 · Cited by 345
Technology and mental health: The role of artificial intelligence
Lovejoy, C. A. (2019) · European Psychiatry · doi:10.1016/j.eurpsy.2018.08.004 · Cited by 129
Artificial Intelligence Chatbot for Depression: Descriptive Study of Usage.
Dosovitsky, G., Pineda, B. S., Jacobson, N. C., Chang, C., Escoredo, M., & Bunge, E. L. (2020) · JMIR Formative Research · doi:10.2196/17065 · Cited by 118
Beyond human expertise: the promise and limitations of ChatGPT in suicide risk assessment
Elyoseph, Z., & Levkovich, I. (2023) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2023.1213141 · Cited by 116
Maurya, R. K. (2024) · Counselling and Psychotherapy Research · doi:10.1002/capr.12699 · Cited by 51
Self-citationPrescott, J., & Hanley, T. (2023) · Mental Health and Social Inclusion · doi:10.1108/mhsi-02-2023-0020 · Cited by 49
Cited by
Torous, J., Linardon, J., Goldberg, S. B., Sun, S., Bell, I., Nicholas, J., Hassan, L., Hua, Y., Milton, A., & Firth, J. (2025) · World Psychiatry · doi:10.1002/wps.21299 · Cited by 323
Hua, Y., Siddals, S., Ma, Z., Galatzer‐Levy, I., Xia, W., Hau, C., Na, H., Flathers, M., Linardon, J., Ayubcha, C., et al. (2025) · World Psychiatry · doi:10.1002/wps.21352 · Cited by 117
Evaluating Generative AI in Mental Health: Systematic Review of Capabilities and Limitations
Wang, L., Bhanushali, T., Huang, Z., Yang, J., Badami, S., & Hightow-Weidman, L. (2025) · JMIR Mental Health · doi:10.2196/70014 · Cited by 73
“The specific therapy skill examined in the studies includes psychoeducation [20-22,28] Five studies had specific use cases when evaluating the capabilities of GenAI models, including psychoeducation or counseling for erectile dysfunction [20], diagnosis of AD and CN [25], prognostic assessment of…”
InfluentialLuo, X., Wang, Z., Tilley, J. L., Balarajan, S., Bassey, U.-A., & Cheang, C. I. (2025) · JMIR Mental Health · doi:10.2196/77951 · Cited by 48
“…better than the general population in addressing open-ended questions involving emotionally intense situations [5], and can provide reliable psychoeducation advice for mental health prompts [6], suggesting their potential in providing responses that are relevant and useful for mental health issues.”
Goldie, J., Dennis, S., Hipgrave, L., & Coleman, A. (2025) · JMIR Human Factors · doi:10.2196/71065 · Cited by 7
“Preprint and peer-reviewed studies assessing the quality of psycho-educational information generated by ChatGPT on depression, anxiety, psychosis, and substance abuse found that it was accurate, clear, clinically useful, relevant, and empa-thetic [11-13].”
Metadata
- Authors
- Maurya, R. K., Montesinos, S., Bogomaz, M., & DeDiego, A. C.
- Venue
- Counselling and Psychotherapy Research
- Publisher
- Wiley
- Published
- 2024-04-25
- Volume
- 25
- Issue
- 1
- ISSN
- 1473-3145 (ISSN-L)
- 1746-1405
- OpenAlex
- W4395669968
- Cited by
- 44
- References
- 13
- FWCI
- 15.98
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.