Abstract

Human to virtual human interaction may be regarded as the next frontier in interface design, particularly for tasks that are social or collaborative in nature. Virtual human interfaces or embodied conversational agents, while challenging to develop and evaluate, have the potential to revolutionize the accessibility, usability, and applicability of computers in everyday life. My primary area of research lies in understanding the impact of social functions in human-virtual human interaction. Specifically, the goal of my work is to investigate what social or conversational tasks are best suited for a virtual human interface agent, and how these capabilities affect social factors such as engagement, satisfaction, acceptance of the interface agent's role, and the success of task performance in an interactive social or public setting. To this end, I present the Virtual Human Interface Framework (VHIF) implemented for the purpose of studying human-virtual human interaction. In this talk I also present Marve, a virtual receptionist, created as a proof-of-concept application built using VHIF. Using Marve, I studied the impact of the agent's social conversational capabilities on users' perceptions and treatment of a virtual human interface agent in a deployed public setting. I showed that the virtual human interface agent was able to engage users in context independent social dialogue a significant amount of time. In a controlled study, I also demonstrated that users can be trained in verbal and non-verbal social conversational protocols using natural multi-modal interaction with life-size virtual human interface agents.