"The Role of Choice and Customization on Users' Interaction with Embodied Conversational Agents: Effects on Perception and Performance" CHI 2007 full paper    "Empirical Studies on Embodied Conversational Agents" Ph.D. Dissertation    "ECA as User Interface Paradigm: Experimental Findings within a Framework for Research" in Ruttkay, Z. and Pelachaud, C. Eds. From Brows to Trust: Evaluating Embodied Conversational Agents    "An Empirical Study of the Effects of Agent Competence on User Performance and Perception" AAMAS '04    "An Empirical Study of the Effects of Agent Competence on User Performance and Perception" Tech Report GIT-GVU-04-03     "Be Quiet? Evaluating Proactive and Reactive User Interface Assistants" INTERACT '03     "Be Quiet? Evaluating Proactive and Reactive User Interface Assistants" Tech Report GIT-GVU-03-03    "Anthropomorphic agents as a user interface paradigm: Experimental findings and a framework for research" CogSci '02     "Anthropomorphic agents as a user interface paradigm: Experimental findings and a framework for research" Tech Report GIT-GVU-02-10

Agent-based interfaces, particularly those with anthropomorphic appearance, promise a new paradigm for user interfaces. The traditional view of computers as a tool for functional purposes is challenged by human-like assistants that answer questions and perform tasks through conversational, natural language-style dialogs with users. However, although such assistants have been developed in many applications, little careful empirical evaluation on anthropomorphic interfaces is actually being performed, and the results from this research have been contradictory or equivocal. The goal of our research is to gather a set of experimental data in order to understand the conditions under which users could best benefit from such social interaction.

Our particular foci are two: evaluating this style of interface for its utility/usability and examining ways to build toolkit for such interface. The very long term goal is to generalize our findings and incorporate what we learned into computer systems that we will interact with in our everyday life of near future.