Storytelling Agents with Personality and Adaptivity

TL;DR

This paper investigates how virtual storytelling agents can express personality traits and adaptivity through gestures, showing that users perceive these variations and prefer adaptive agents, regardless of story content or gender.

Contribution

It demonstrates that virtual agents' gestures can effectively convey personality and adaptivity, and that users prefer adaptive agents in storytelling contexts.

Findings

Subjects perceive extraversion variations regardless of story or gender.

Subjects prefer adaptive virtual agents over nonadaptive ones.

Perceived personality traits are consistent across different stories and agent genders.

Abstract

We explore the expression of personality and adaptivity through the gestures of virtual agents in a storytelling task. We conduct two experiments using four different dialogic stories. We manipulate agent personality on the extraversion scale, whether the agents adapt to one another in their gestural performance and agent gender. Our results show that subjects are able to perceive the intended variation in extraversion between different virtual agents, independently of the story they are telling and the gender of the agent. A second study shows that subjects also prefer adaptive to nonadaptive virtual agents.