Embodied Conversational Agents in Extended Reality: A Systematic Review
Fu‐Chia Yang, Pedro Acevedo, Siqi Guo, Minsoo Choi, Christos Mousas
Abstract
Embodied conversational agents (ECAs) that can interact with users in a human-like manner have demonstrated promising potential in various endeavors. With the ongoing advancement in extended reality (XR) and artificial intelligence (AI), ECAs are becoming increasingly sophisticated. Although previous reviews predominantly focused on ECAs for non-XR applications, there is a growing number of research exploring the capabilities of ECAs utilizing XR technologies. Our work identified the gap between the existing reviews and the current trends in XR ECAs. We began with 1717 related papers from 01/2014 to 06/2024. We narrowed them down to 23 papers through the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework with an iterative screening procedure and criteria defined by our research team. The resulting papers were analyzed and discussed with respect to the features of the ECA application, design and implementation, and use cases. This systematic review aimed to provide trending insights that would benefit the research community in the future development of XR ECAs.