MétaCan
Menu
Back to cohort
Record W4410110516 · doi:10.2196/68056

Leveraging Large Language Models for Simulated Psychotherapy Client Interactions: Development and Usability Study of Client101

2025· article· en· W4410110516 on OpenAlexvenueno aff
Daniel Cabrera Lozoya, Mike Conway, Edoardo Sebastiano De Duro, Simon D’Alfonso

Bibliographic record

VenueJMIR Medical Education · 2025
Typearticle
Languageen
FieldPsychology
TopicDigital Mental Health Interventions
Canadian institutionsnot available
Fundersnot available
KeywordsPreprintUsabilityComputer scienceHuman–computer interactionPsychologyWorld Wide Web

Abstract

fetched live from OpenAlex

Background: 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. Objective: We aim to develop and test a web-based conversational psychotherapy training tool designed to closely resemble clients with mental health issues. Methods: 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's 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-42 sessions related to anxiety and 47 related to depression-using an independent samples t test. Results: Participants' survey responses were predominantly positive regarding the chatbots' 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 (t56=4.03, P=.001), family (t56=-8.62, P=.001), and negative emotions (t56=-3.91, P=.002). The remaining 5 features-sadness, personal pronouns, present focus, social, and anger-did not show significant differences. For depression-related features, 4 of 9 showed significant differences: negative emotions (t60=-3.84, P=.003), feeling (t60=-6.40, P<.001), health (t60=-4.13, P=.001), and illness (t60=-5.52, P<.001). The other 5 features-sadness, anxiety, mental, first-person pronouns, and discrepancy-did not show statistically significant differences. Conclusions: 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's effectiveness as a tool for training mental health professionals.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.815
Threshold uncertainty score0.373

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.042
GPT teacher head0.486
Teacher spread0.444 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designOther design
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations8
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueJMIR Medical EducationSame topicDigital Mental Health InterventionsFrench-language works237,207