Evaluating the efficacy of Amanda: A voice-based large language model chatbot for relationship challenges

Digital health interventions are increasingly necessary to bridge gaps in mental health care, providing scalable and accessible solutions to address unmet needs. Relationship challenges, a significant driver of individual well-being and distress, are often under-supported due to barriers such as sti...

Full description

Saved in:
Bibliographic Details
Main Authors: Laura M. Vowels, Shannon K. Sweeney, Matthew J. Vowels
Format: Article
Language:English
Published: Elsevier 2025-05-01
Series:Computers in Human Behavior: Artificial Humans
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2949882125000258
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850183160468340736
author Laura M. Vowels
Shannon K. Sweeney
Matthew J. Vowels
author_facet Laura M. Vowels
Shannon K. Sweeney
Matthew J. Vowels
author_sort Laura M. Vowels
collection DOAJ
description Digital health interventions are increasingly necessary to bridge gaps in mental health care, providing scalable and accessible solutions to address unmet needs. Relationship challenges, a significant driver of individual well-being and distress, are often under-supported due to barriers such as stigma, cost, and limited access to trained therapists. This study evaluates Amanda, a GPT-4-powered voice-based chatbot, designed to deliver single-session relationship support and enhance therapeutic engagement through natural and collaborative interactions. Participants (N = 54) completed a range of clinical outcome measures and their attitudes toward chatbots and digital health interventions pre- and post-intervention as well as two weeks later. In the interactions with the chatbot, the participants explored a range of relational issues and reported significant improvements in problem-specific outcomes, including reduced distress, enhanced communication, and greater confidence in managing conflicts directly after the interaction as well as two weeks later. While generic relationship outcomes showed only delayed improvements, individual well-being did not significantly change. Participants rated Amanda highly on usability, therapeutic skills, and working alliance, with reduced repetitiveness compared to the text-based version. These findings underscore the potential of voice-based chatbots to deliver accessible and effective relationship support. Future research should explore multi-session formats, clinical populations, and comparisons with other large language models to refine and expand AI-powered interventions.
format Article
id doaj-art-775471532af044178a3e1f3e98c37ed1
institution OA Journals
issn 2949-8821
language English
publishDate 2025-05-01
publisher Elsevier
record_format Article
series Computers in Human Behavior: Artificial Humans
spelling doaj-art-775471532af044178a3e1f3e98c37ed12025-08-20T02:17:25ZengElsevierComputers in Human Behavior: Artificial Humans2949-88212025-05-01410014110.1016/j.chbah.2025.100141Evaluating the efficacy of Amanda: A voice-based large language model chatbot for relationship challengesLaura M. Vowels0Shannon K. Sweeney1Matthew J. Vowels2School of Psychology, University of Roehampton, UK; Institute of Psychology, University of Lausanne, Lausanne, Switzerland; Corresponding author. School of Psychology, Whitelands College, University of Roehampton, Holybourne Ave, London, SW15 4JD, UK.Institute of Psychology, University of Lausanne, Lausanne, SwitzerlandInstitute of Psychology, University of Lausanne, Lausanne, Switzerland; The Sense Innovation and Research Center, Sion, Lausanne, Switzerland; Radiology Department, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland; Centre for Vision Speech and Signal Processing, University of Surrey, Guildford, UKDigital health interventions are increasingly necessary to bridge gaps in mental health care, providing scalable and accessible solutions to address unmet needs. Relationship challenges, a significant driver of individual well-being and distress, are often under-supported due to barriers such as stigma, cost, and limited access to trained therapists. This study evaluates Amanda, a GPT-4-powered voice-based chatbot, designed to deliver single-session relationship support and enhance therapeutic engagement through natural and collaborative interactions. Participants (N = 54) completed a range of clinical outcome measures and their attitudes toward chatbots and digital health interventions pre- and post-intervention as well as two weeks later. In the interactions with the chatbot, the participants explored a range of relational issues and reported significant improvements in problem-specific outcomes, including reduced distress, enhanced communication, and greater confidence in managing conflicts directly after the interaction as well as two weeks later. While generic relationship outcomes showed only delayed improvements, individual well-being did not significantly change. Participants rated Amanda highly on usability, therapeutic skills, and working alliance, with reduced repetitiveness compared to the text-based version. These findings underscore the potential of voice-based chatbots to deliver accessible and effective relationship support. Future research should explore multi-session formats, clinical populations, and comparisons with other large language models to refine and expand AI-powered interventions.http://www.sciencedirect.com/science/article/pii/S2949882125000258ChatbotsArtificial intelligenceRelationship supportLarge language modelsVoice-based interventionsDigital therapy
spellingShingle Laura M. Vowels
Shannon K. Sweeney
Matthew J. Vowels
Evaluating the efficacy of Amanda: A voice-based large language model chatbot for relationship challenges
Computers in Human Behavior: Artificial Humans
Chatbots
Artificial intelligence
Relationship support
Large language models
Voice-based interventions
Digital therapy
title Evaluating the efficacy of Amanda: A voice-based large language model chatbot for relationship challenges
title_full Evaluating the efficacy of Amanda: A voice-based large language model chatbot for relationship challenges
title_fullStr Evaluating the efficacy of Amanda: A voice-based large language model chatbot for relationship challenges
title_full_unstemmed Evaluating the efficacy of Amanda: A voice-based large language model chatbot for relationship challenges
title_short Evaluating the efficacy of Amanda: A voice-based large language model chatbot for relationship challenges
title_sort evaluating the efficacy of amanda a voice based large language model chatbot for relationship challenges
topic Chatbots
Artificial intelligence
Relationship support
Large language models
Voice-based interventions
Digital therapy
url http://www.sciencedirect.com/science/article/pii/S2949882125000258
work_keys_str_mv AT lauramvowels evaluatingtheefficacyofamandaavoicebasedlargelanguagemodelchatbotforrelationshipchallenges
AT shannonksweeney evaluatingtheefficacyofamandaavoicebasedlargelanguagemodelchatbotforrelationshipchallenges
AT matthewjvowels evaluatingtheefficacyofamandaavoicebasedlargelanguagemodelchatbotforrelationshipchallenges