Are We Generalizing from the Exception? An In-the-Wild Study on Group-Sensitive Conversation Design in Human-Agent Interactions

TL;DR

This study explores how group-sensitive conversation design affects human-agent interactions in real-world settings, revealing challenges and insights for improving multi-party dialogue adaptation in social agents.

Contribution

It provides an in-the-wild evaluation of group-adaptive conversation strategies across different agent embodiments, highlighting limitations and future directions.

Findings

No significant effect on perceived satisfaction.

Challenges in adapting CAI for multi-party interactions.

Differences observed between robot and virtual agent interactions.

Abstract

This paper investigates the impact of a group-adaptive conversation design in two socially interactive agents (SIAs) through two real-world studies. Both SIAs - Furhat, a social robot, and MetaHuman, a virtual agent - were equipped with a conversational artificial intelligence (CAI) backend combining hybrid retrieval and generative models. The studies were carried out in an in-the-wild setting with a total of $N = 188$ participants who interacted with the SIAs - in dyads, triads or larger groups - at a German museum. Although the results did not reveal a significant effect of the group-sensitive conversation design on perceived satisfaction, the findings provide valuable insights into the challenges of adapting CAI for multi-party interactions and across different embodiments (robot vs.\ virtual agent), highlighting the need for multimodal strategies beyond linguistic pluralization. These insights contribute to the fields of Human-Agent Interaction (HAI), Human-Robot Interaction (HRI), and broader Human-Machine Interaction (HMI), providing insights for future research on effective dialogue adaptation in group settings.