The Challenge of Constructing Psychologically Believable Agents

Embodied conversational agents (ECAs) are designed to provide natural and intuitive communication with a human user. One major current topic in agent design consequently is to enhance their believability, often by incorporating internal models of emotions or motivations. As psychological theories often lack the necessary details for direct implementation, many agent modelers currently rely on models that are rather marginal in current psychological research, or models that are created ad hoc with little theoretical and empirical foundation. The goal of this article is both to raise psychologists' awareness of the central challenges in the process of creating psychologically believable agents, and to recommend existing psychological frameworks to the virtual agentscommunity that seem particularly useful for implementation in ECAs. Special attention is paid to a computationally detailed model of basic social motives that seems particularly useful for implementation: the Zurich model of social motivation.