{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T16:36:45Z","timestamp":1791391005476,"version":"4.3.3"},"reference-count":42,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Educ"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n In recent years, large language models (LLMs) have shown a remarkable ability to generate human-like text. One potential application of this capability is using LLMs to simulate clients in a mental health context. This research presents the development and evaluation of Client101, a web conversational platform featuring LLM-driven chatbots designed to simulate mental health clients.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n We aim to develop and test a web-based conversational psychotherapy training tool designed to closely resemble clients with mental health issues.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n \n We used GPT-4 and prompt engineering techniques to develop chatbots that simulate realistic client conversations. Two chatbots were created based on clinical vignette cases: one representing a person with depression and the other, a person with generalized anxiety disorder. A total of 16 mental health professionals were instructed to conduct single sessions with the chatbots using a cognitive behavioral therapy framework; a total of 15 sessions with the anxiety chatbot and 14 with the depression chatbot were completed. After each session, participants completed a 19-question survey assessing the chatbot\u2019s ability to simulate the mental health condition and its potential as a training tool. Additionally, we used the LIWC (Linguistic Inquiry and Word Count) tool to analyze the psycholinguistic features of the chatbot conversations related to anxiety and depression. These features were compared to those in a set of webchat psychotherapy sessions with human clients\u201442 sessions related to anxiety and 47 related to depression\u2014using an independent samples\n t<\/jats:italic>\n test.\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n Participants\u2019 survey responses were predominantly positive regarding the chatbots\u2019 realism and portrayal of mental health conditions. For instance, 93% (14\/15) considered that the chatbot provided a coherent and convincing narrative typical of someone with an anxiety condition. The statistical analysis of LIWC psycholinguistic features revealed significant differences between chatbot and human therapy transcripts for 3 of 8 anxiety-related features: negations (\n t<\/jats:italic>\n 56<\/jats:sub>\n =4.03,\n P<\/jats:italic>\n =.001), family (\n t<\/jats:italic>\n 56<\/jats:sub>\n =\u20138.62,\n P<\/jats:italic>\n =.001), and negative emotions (\n t<\/jats:italic>\n 56<\/jats:sub>\n =\u20133.91,\n P<\/jats:italic>\n =.002). The remaining 5 features\u2014sadness, personal pronouns, present focus, social, and anger\u2014did not show significant differences. For depression-related features, 4 of 9 showed significant differences: negative emotions (\n t<\/jats:italic>\n 60<\/jats:sub>\n =\u20133.84,\n P<\/jats:italic>\n =.003), feeling (\n t<\/jats:italic>\n 60<\/jats:sub>\n =\u20136.40,\n P<\/jats:italic>\n <.001), health (\n t<\/jats:italic>\n 60<\/jats:sub>\n =\u20134.13,\n P<\/jats:italic>\n =.001), and illness (\n t<\/jats:italic>\n 60<\/jats:sub>\n =\u20135.52,\n P<\/jats:italic>\n <.001). The other 5 features\u2014sadness, anxiety, mental, first-person pronouns, and discrepancy\u2014did not show statistically significant differences.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n This research underscores both the strengths and limitations of using GPT-4-powered chatbots as tools for psychotherapy training. Participant feedback suggests that the chatbots effectively portray mental health conditions and are generally perceived as valuable training aids. However, differences in specific psycholinguistic features suggest targeted areas for enhancement, helping refine Client101\u2019s effectiveness as a tool for training mental health professionals.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/68056","type":"journal-article","created":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T14:50:06Z","timestamp":1746543006000},"page":"e68056-e68056","source":"Crossref","is-referenced-by-count":24,"title":["Leveraging Large Language Models for Simulated Psychotherapy Client Interactions: Development and Usability Study of Client101"],"prefix":"10.2196","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1501-7804","authenticated-orcid":false,"given":"Daniel","family":"Cabrera Lozoya","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3209-8108","authenticated-orcid":false,"given":"Mike","family":"Conway","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9204-3203","authenticated-orcid":false,"given":"Edoardo","family":"Sebastiano De Duro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7407-8730","authenticated-orcid":false,"given":"Simon","family":"D'Alfonso","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,7,31]]},"reference":[{"issue":"3","key":"R1","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1080\/10503300600612241","article-title":"The impact of psychotherapy training: introduction to the special section","volume":"16","author":"R\u00f8nnestad","journal-title":"Psychother Res"},{"issue":"7","key":"R2","doi-asserted-by":"publisher","DOI":"10.2196\/12529","article-title":"Development and evaluation of clientbot: patient-like conversational agent to train basic counseling skills","volume":"21","author":"Tanana","journal-title":"J Med Internet Res"},{"issue":"7","key":"R3","doi-asserted-by":"publisher","first-page":"456","DOI":"10.1177\/0706743719828977","article-title":"Chatbots and conversational agents in mental health: a review of the psychiatric landscape","volume":"64","author":"Vaidyam","journal-title":"Can J Psychiatry"},{"key":"R4","doi-asserted-by":"crossref","unstructured":"Frangoudes F Hadjiaros M Schiza EC Matsangidou M Tsivitanidou O Neokleous K . An overview of the use of chatbots in medical and healthcare education. In: Zaphiris P Ioannou A , editors. Learning and Collaboration Technologies: Games and Virtual Environments for Learning. Springer; 2021:170-184. [doi: 10.1007\/978-3-030-77943-6_11]","DOI":"10.1007\/978-3-030-77943-6_11"},{"key":"R5","doi-asserted-by":"crossref","unstructured":"Dryden W . Single-Session Integrated CBT. Routledge; 2021. [doi: 10.4324\/9781003214557]","DOI":"10.4324\/9781003214557"},{"issue":"1","key":"R6","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1145\/365153.365168","article-title":"ELIZA\u2014a computer program for the study of natural language communication between man and machine","volume":"9","author":"Weizenbaum","journal-title":"Commun ACM"},{"issue":"1","key":"R7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/0004-3702(71)90002-6","article-title":"Artificial paranoia","volume":"2","author":"Colby","journal-title":"Artif Intell"},{"issue":"1","key":"R8","doi-asserted-by":"publisher","DOI":"10.2196\/17828","article-title":"Perceptions and opinions of patients about mental health chatbots: scoping review","volume":"23","author":"Abd-Alrazaq","journal-title":"J Med Internet Res"},{"key":"R9","doi-asserted-by":"crossref","unstructured":"Adamopoulou E Moussiades L . An overview of chatbot technology. In: Maglogiannis I Iliadis L Pimenidis E , editors. Artificial Intelligence Applications and Innovations. Springer; 2020:373-383. [doi: 10.1007\/978-3-030-49186-4_31] ISBN: 978-3-030-49185-7","DOI":"10.1007\/978-3-030-49186-4_31"},{"key":"R10","unstructured":"Vinyals O Le Q . A neural conversational model. arXiv. Preprint posted online on Jun 19, 2015. [doi: 10.48550\/arXiv.1506.05869]"},{"key":"R11","unstructured":"Lison P Tiedemann J . OpenSubtitles2016: extracting large parallel corpora from movie and TV subtitles. In: Calzolari N Choukri K Declerck T Goggi S Grobelnik M Maegaard B Mariani J Mazo H Moreno A Odijk J Piperidis S , editors. Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC\u201916) Portoro\u017e. European Language Resources Association (ELRA); 2016:923-929."},{"key":"R12","unstructured":"Alexander Street Press. Counseling and psychotherapy transcripts: volume I. Redivis; 2023. [doi: 10.57761\/C9DA-ZQ22]"},{"key":"R13","doi-asserted-by":"crossref","unstructured":"Zhang S Dinan E Urbanek J Szlam A Kiela D Weston J . Personalizing dialogue agents: i have a dog, do you have pets too? Presented at: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers); Jul 15-20, 2018; Melbourne, Australia. [doi: 10.18653\/v1\/P18-1205]","DOI":"10.18653\/v1\/P18-1205"},{"key":"R14","doi-asserted-by":"crossref","unstructured":"Zhang Y Sun S Galley M et al. DIALOGPT: large-scale generative pre-training for conversational response generation. Presented at: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics; Jul 6-8, 2020:270-278; URL: https:\/\/www.aclweb.org\/anthology\/2020.acl-demos [Accessed 04-06-2025] [doi: 10.18653\/v1\/2020.acl-demos.30]","DOI":"10.18653\/v1\/2020.acl-demos.30"},{"key":"R15","unstructured":"Li Y Zeng C Zhong J Zhang R Zhang M Zou L . Leveraging large language model as simulated patients for clinical education. arXiv. Preprint posted online on Apr 13, 2024. [doi: 10.48550\/arXiv.2404.13066]"},{"key":"R16","unstructured":"Stapleton L Taylor J Fox S Wu T Zhu H . Seeing seeds beyond weeds: green teaming generative AI for beneficial uses. arXiv. Preprint posted online on May 30, 2023. [doi: 10.48550\/arXiv.2306.03097]"},{"key":"R17","doi-asserted-by":"crossref","unstructured":"Demasi O Hearst MA Recht B . Towards augmenting crisis counselor training by improving message retrieval. Presented at: Proceedings of the Sixth Workshop on Computational Linguistics and Clinical Psychology; Jun 6-8, 2019; Minneapolis, Minnesota. [doi: 10.18653\/v1\/W19-3001]","DOI":"10.18653\/v1\/W19-3001"},{"issue":"1","key":"R18","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-0233-7","article-title":"Methods in predictive techniques for mental health status on social media: a critical review","volume":"3","author":"Chancellor","journal-title":"NPJ Digit Med"},{"key":"R19","unstructured":"Boyd RL Ashokkumar A Seraj S Pennebaker JW . The development and psychometric properties of LIWC-22. The University of Texas at Austin; 2022. [doi: 10.13140\/RG.2.2.23890.43205]"},{"issue":"44","key":"R20","doi-asserted-by":"publisher","first-page":"11203","DOI":"10.1073\/pnas.1802331115","article-title":"Facebook language predicts depression in medical records","volume":"115","author":"Eichstaedt","journal-title":"Proc Natl Acad Sci U S A"},{"key":"R21","doi-asserted-by":"publisher","DOI":"10.3389\/fdgth.2022.779039","article-title":"Toward linguistic recognition of generalized anxiety disorder","volume":"4","author":"Rook","journal-title":"Front Digit Health"},{"key":"R22","unstructured":"OpenAIAchiam J Adler S . GPT-4 technical report. arXiv. Preprint posted online on Mar 15, 2023. [doi: 10.48550\/arXiv.2303.08774]"},{"key":"R23","doi-asserted-by":"crossref","unstructured":"Madaan A Tandon N Clark P Yang Y . Memory-assisted prompt editing to improve GPT-3 after deployment. Presented at: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing; Dec 7-11, 2022; Abu Dhabi, United Arab Emirates. [doi: 10.18653\/v1\/2022.emnlp-main.183]","DOI":"10.18653\/v1\/2022.emnlp-main.183"},{"key":"R24","doi-asserted-by":"crossref","unstructured":"Kong A Zhao S Chen H et al. Better zero-shot reasoning with role-play prompting. Presented at: Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics; Jun 16-21, 2024; Mexico City, Mexico. [doi: 10.18653\/v1\/2024.naacl-long.228]","DOI":"10.18653\/v1\/2024.naacl-long.228"},{"key":"R25","doi-asserted-by":"crossref","unstructured":"Sipe WEB Eisendrath SJ . Chapter 3 - mindfulness-based cognitive therapy for treatment-resistant depression. In: Baer RA , editor. Mindfulness-Based Treatment Approaches. 2nd ed. Academic Press; 2014:61-76. [doi: 10.1016\/B978-0-12-416031-6.00003-7] ISBN: 978-0-12-416031-6","DOI":"10.1016\/B978-0-12-416031-6.00003-7"},{"key":"R26","unstructured":"NICE. Generalised Anxiety Disorder and Panic Disorder in Adults: Management. London: National Institute for Health and Care Excellence (NICE); 2019. ISBN: 978-1-4731-2854-5"},{"issue":"3","key":"R27","doi-asserted-by":"publisher","DOI":"10.2196\/jmir.6.3.e34","article-title":"Improving the quality of web surveys: the Checklist for Reporting Results of Internet E-Surveys (CHERRIES)","volume":"6","author":"Eysenbach","journal-title":"J Med Internet Res"},{"key":"R28","doi-asserted-by":"crossref","unstructured":"Holmes S Moorhead A Bond R Zheng H Coates V Mctear M . Usability testing of a healthcare chatbot: can we use conventional methods to assess conversational user interfaces? Presented at: ECCE \u201919: Proceedings of the 31st European Conference on Cognitive Ergonomics; Sep 10, 2019; Belfast, United Kingdom. [doi: 10.1145\/3335082.3335094]","DOI":"10.1145\/3335082.3335094"},{"issue":"8","key":"R29","doi-asserted-by":"publisher","DOI":"10.2196\/17155","article-title":"A novel multimodal digital service (moderated online social therapy+) for help-seeking young people experiencing mental ill-health: pilot evaluation within a national youth e-mental health service","volume":"22","author":"Alvarez-Jimenez","journal-title":"J Med Internet Res"},{"issue":"2","key":"R30","doi-asserted-by":"publisher","first-page":"175","DOI":"10.3758\/BF03193146","article-title":"G*Power 3: a flexible statistical power analysis program for the social, behavioral, and biomedical sciences","volume":"39","author":"Faul","journal-title":"Behav Res Methods"},{"issue":"4","key":"R31","doi-asserted-by":"publisher","first-page":"1149","DOI":"10.3758\/BRM.41.4.1149","article-title":"Statistical power analyses using G*Power 3.1: tests for correlation and regression analyses","volume":"41","author":"Faul","journal-title":"Behav Res Methods"},{"key":"R32","unstructured":"Brahman F Kumar S Balachandran V et al. The art of saying no: contextual noncompliance in language models. Presented at: 38th Conference on Neural Information Processing Systems (NeurIPS 2024) Track on Datasets and Benchmarks; Dec 10-15, 2024; Vancouver, Canada."},{"key":"R33","unstructured":"Li Z Chen G Shao R Xie Y Jiang D Nie L . Enhancing emotional generation capability of large language models via emotional chain-of-thought. arXiv. Preprint posted online on Jan 12, 2024. [doi: 10.48550\/arXiv.2401.06836]"},{"key":"R34","doi-asserted-by":"crossref","unstructured":"Lozoya D Berazaluce A Perches J L\u00faa E Conway M D\u2019Alfonso S . Generating mental health transcripts with SAPE (spanish adaptive prompt engineering). In: Duh K Gomez H Bethard S , editors. Presented at: Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics; Jun 16-21, 2024; Mexico City, Mexico. [doi: 10.18653\/v1\/2024.naacl-long.285]","DOI":"10.18653\/v1\/2024.naacl-long.285"},{"key":"R35","doi-asserted-by":"crossref","unstructured":"Lozoya DC D\u2019Alfonso S Conway M . Identifying gender bias in generative models for mental health synthetic data. Presented at: 2023 IEEE 11th International Conference on Healthcare Informatics (ICHI); Jun 26-29, 2023; Houston, TX. [doi: 10.1109\/ICHI57859.2023.00109]","DOI":"10.1109\/ICHI57859.2023.00109"},{"key":"R36","doi-asserted-by":"crossref","unstructured":"Abid A Farooqi M Zou J . Persistent anti-muslim bias in large language models. Presented at: AIES \u201921; May 19-21, 2021. URL: https:\/\/dl.acm.org\/doi\/proceedings\/10.1145\/3461702 [Accessed 04-06-2025] [doi: 10.1145\/3461702.3462624]","DOI":"10.1145\/3461702.3462624"},{"key":"R37","doi-asserted-by":"crossref","unstructured":"Shihadeh J Ackerman M Troske A Lawson N Gonzalez E . Brilliance bias in GPT-3. Presented at: 2022 IEEE Global Humanitarian Technology Conference (GHTC); Sep 8-11, 2022; Santa Clara, CA. [doi: 10.1109\/GHTC55712.2022.9910995]","DOI":"10.1109\/GHTC55712.2022.9910995"},{"issue":"2","key":"R38","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1111\/j.1467-9280.2009.02282.x","article-title":"The role of gender in mental-illness stigma","volume":"20","author":"Wirth","journal-title":"Psychol Sci"},{"issue":"4","key":"R39","doi-asserted-by":"publisher","first-page":"1557988320949322","DOI":"10.1177\/1557988320949322","article-title":"Males and mental health stigma","volume":"14","author":"Chatmon","journal-title":"Am J Mens Health"},{"issue":"1","key":"R40","doi-asserted-by":"publisher","first-page":"21","DOI":"10.4103\/0253-7176.96151","article-title":"Boundary crossings and violations in clinical settings","volume":"34","author":"Aravind","journal-title":"Indian J Psychol Med"},{"key":"R41","doi-asserted-by":"crossref","unstructured":"Natale S . The ELIZA effect: Joseph Weizenbaum and the emergence of chatbots. In: Deceitful Media. Oxford Academic; 2021:50-67. [doi: 10.1093\/oso\/9780190080365.003.0004] ISBN: 978-0-19-008036-5","DOI":"10.1093\/oso\/9780190080365.003.0004"},{"key":"R42","doi-asserted-by":"publisher","DOI":"10.2196\/60432","article-title":"Exploring the ethical challenges of conversational ai in mental health care: scoping review","volume":"12","author":"Meadi","journal-title":"JMIR Ment Health"}],"container-title":["JMIR Medical Education"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/mededu.jmir.org\/2025\/1\/e68056","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T22:27:22Z","timestamp":1785536842000},"score":1,"resource":{"primary":{"URL":"https:\/\/mededu.jmir.org\/2025\/1\/e68056"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,31]]},"references-count":42,"URL":"https:\/\/doi.org\/10.2196\/68056","relation":{},"ISSN":["2369-3762"],"issn-type":[{"value":"2369-3762","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,31]]},"article-number":"v11i3e68056"}}