Avatar led interventions in the Metaverse reveal that interpersonal effectiveness can be measured, predicted, and improved

Nagendran, A., Compton, S., Follette, W. C., Golenchenko, A., Compton, A. and Grizou, J. (2022) Avatar led interventions in the Metaverse reveal that interpersonal effectiveness can be measured, predicted, and improved. Scientific Reports, 12, 21892. (doi: 10.1038/s41598-022-26326-4)

Abstract

Experiential learning has been known to be an engaging and effective modality for personal and professional development. The Metaverse provides ample opportunities for the creation of environments in which such experiential learning can occur. In this work, we introduce a novel interpersonal effectiveness improvement framework (ELAINE) that combines Artificial Intelligence and Virtual Reality to create a highly immersive and efficient learning experience using avatars. We present findings from a study that uses this framework to measure and improve the interpersonal effectiveness of individuals interacting with an avatar. Results reveal that individuals with deficits in their interpersonal effectiveness show a significant improvement (p < 0.02) after multiple interactions with an avatar. The results also reveal that individuals interact naturally with avatars within this framework, and exhibit similar behavioral traits as they would in the real world. We use this as a basis to analyze the underlying audio and video data streams of individuals during these interactions. We extract relevant features from these data and present a machine-learning based approach to predict interpersonal effectiveness during human-avatar conversation. We conclude by discussing the implications of these findings to build beneficial applications for the real world.

• Item Type: Articles
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Grizou, Dr Jonathan
• Authors: Nagendran, A., Compton, S., Follette, W. C., Golenchenko, A., Compton, A., and Grizou, J.
• College/School: College of Science and Engineering > School of Computing Science
• Journal Name: Scientific Reports
• Publisher: Nature Research
• ISSN: 2045-2322
• ISSN (Online): 2045-2322
• Copyright Holders: Copyright © 2022 The Authors
• First Published: First published in Scientific Reports 12:21892
• Publisher Policy: Reproduced under a Creative Commons licence