Longitudinal studies of human-virtual agent interaction are expensive and time consuming to conduct. We present a new concept and tool for conducting such studies—the virtual laboratory—in which a standing group of study participants interacts periodically with a computer agent that can be remotely manipulated to effect different study conditions, with outcome measures also collected remotely. This architecture allows new experiments to be dynamically defined and immediately implemented in the continuously-running system without delays due to recruitment and system reconfiguration. The use of this tool in the study of a virtual agent that plays the role of an exercise counselor for older adults is described, along with the results of an initial experiment into the effects of conversational variability on user engagement and exercise behavior.
Timothy W. Bickmore, Daniel Schulman