The Effects of Engaging and Affective Behaviors of Virtual Agents in Group Decision-Making

by   Hanseob Kim, et al.

Virtual agents (VAs) need to exhibit engaged and affective behavior in order to become more effective social actors in our daily lives. However, such behaviors need to conform to social norms, especially in organizational settings. This study examines how different VA behaviors influence subjects' perceptions and actions in group decision-making processes. Participants exposed to VAs demonstrated varying levels of engagement and affective behavior during the group discussions. Engagement refers to the VA's focus on the group task, while affective behavior represents the VA's emotional state. The findings indicate that VA engagement positively influences user behavior, particularly in attention allocation. However, it has minimal impact on subjective perception. Conversely, affective expressions of VAs have a negative impact on subjective perceptions, such as social presence, social influence, and trustworthiness. Interestingly, in 64 discussions for tasks, only seven showed a decline in group scores compared to individual scores, and in six of these cases, the VA exhibited a non-engaged and affective state. We discuss the results and the potential implications for future research on using VAs in group meetings. It provides valuable insights for improving VA behavior as a team member in group decision-making scenarios and guides VA design in organizational contexts.


page 2

page 4

page 5

page 6

page 8


Multipar-T: Multiparty-Transformer for Capturing Contingent Behaviors in Group Conversations

As we move closer to real-world AI systems, AI agents must be able to de...

Multimodal Dialogue Management for Multiparty Interaction with Infants

We present dialogue management routines for a system to engage in multip...

The Ways of Words: The Impact of Word Choice on Information Engagement and Decision Making

Little research has explored how information engagement (IE), the degree...

The Influence of Reward on the Social Valence of Interactions

Throughout the years, social norms have been promoted as an informal enf...

Mechanical Chameleons: Evaluating the effects of a social robot's non-verbal behavior on social influence

In this paper we present a pilot study which investigates how non-verbal...

Incentivising cooperation by rewarding the weakest member

Autonomous agents that act with each other on behalf of humans are becom...

Please sign up or login with your details

Forgot password? Click here to reset