Evaluating the Quality of Psychotherapy Conversational Agents: Framework Development and Cross-Sectional Study

• Published in: JMIR formative research Vol. 9; p. e65605
• Main Authors: Sobowale, Kunmi, Humphrey, Daniel Kevin
• Format: Journal Article
• Language: English
• Published: Canada JMIR Publications 02.07.2025
• Subjects: AI-Powered Therapy Bots and Virtual Companions in Digital Mental Health; Artificial Intelligence; Chatbots; Chatbots and Conversational Agents; Communication; Cross-Sectional Studies; Development and Evaluation of Research Methods, Instruments and Tools; Digital Mental Health Interventions, e-Mental Health and Cyberpsychology; Eating behavior; Generative artificial intelligence; Generative Language Models Including ChatGPT; Humans; Large language models; Mental disorders; Mental health care; Original Paper; Popularity; Privacy; Psychotherapy; Psychotherapy - methods; Psychotherapy - standards; Research Instruments, Questionnaires, and Tools; Telemedicine; Therapists; Therapy; psychotherapy chatbots; treatment; evaluation study; generative AI; accessibility; researchers; risk evaluation; therapy; AI; psychotherapy; artificial intelligence; conversational agent; digital health; therapeutic alliance; ChatGPT; chatbots; clinicians; large language models; evaluation framework
• ISSN: 2561-326X; 2561-326X
• DOI: 10.2196/65605

Despite potential risks, artificial intelligence-based chatbots that simulate psychotherapy are becoming more widely available and frequently used by the general public. A comprehensive way of evaluating the quality of these chatbots is needed. To address this need, we developed the CAPE (Conversati...