Usability, acceptance, and the role of realism in virtual humans for breathing exercise training

Abstract

Breathing exercises are used to address a multitude of issues ranging from mental health to physical well-being. While they are recommended for various health conditions, access to professional support is often limited due to time and cost constraints. Virtual Reality technology offers a promising solution for enhancing mindfulness and relaxation practices, including breathing exercises. In our study, we explored the effectiveness of a computer-generated "virtual breathing coach". Our virtual coach has a human appearance, speaks in a human voice, and displays breathing physiology while guiding the participants through a set of breathing exercises of different cycle lengths. The agent exhibits breathing behaviour with the aim of augmenting the influence the agent exerts through the mechanisms of physiological entrainment known from human-to-human interaction. Our empirical, exploratory study with 20 participants, was conducted using non-immersive VR where the system ran on a web browser. On the one hand, we investigated the perception of the virtual human coach, and on the other hand, we evaluated the usability, acceptability, and adherence of the system. We also evaluated the role of realism in acceptance of and adherence to the virtual coach. Participants' responses were recorded using questionnaires. Participants were influenced by the virtual coach and adhered to it if they perceived the virtual coach as more realistic. The participants reported that the system ran well, and they would be willing to continue using the system in the future. Although the virtual human-to-human interaction experience provided by our system is not on par with the naturalistic human-to-human interaction, the results indicate that people are willing to replace a real human coach with a virtual coach. Systems like this are a step towards improving the affordability and on-demand access to another human, such as a coach in our system, especially where access and affordability are limited such as in healthcare. The qualities such as trust and likeability in an embodied interaction can make this interaction more efficient and effective.

Publication DOI: https://doi.org/10.1038/s41598-024-82886-7
Divisions: College of Engineering & Physical Sciences > School of Computer Science and Digital Technologies > Applied AI & Robotics
College of Engineering & Physical Sciences > Aston Centre for Artifical Intelligence Research and Application
College of Engineering & Physical Sciences
Funding Information: No funds, grants, or other support was received.
Additional Information: Copyright © 2025, The Author(s). This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (https://creativecommons.org/licenses/by-nc-nd/4.0/), which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.
Uncontrolled Keywords: Humans,Virtual Reality,Breathing Exercises/methods,User-Computer Interface
Publication ISSN: 2045-2322
Data Access Statement: The datasets generated during and/or analysed during the current study are available from the corresponding author on reasonable request.
Last Modified: 28 Mar 2025 08:11
Date Deposited: 10 Jan 2025 18:10
Full Text Link:
Related URLs: https://www.nat ... 598-024-82886-7 (Publisher URL)
http://www.scop ... tnerID=8YFLogxK (Scopus URL)
PURE Output Type: Article
Published Date: 2025-01-09
Accepted Date: 2024-12-10
Authors: Dar, Sanobar
Ekart, Aniko (ORCID Profile 0000-0001-6967-5397)
Bernardet, Ulysses (ORCID Profile 0000-0003-4659-3035)

Export / Share Citation


Statistics

Additional statistics for this record