Virtually Bad: A Study on Virtual Agents that Physically Threaten Human Beings

This paper introduces the concept of “virtual bad guys”: intelligent virtual agents that take a negative or even aggressive stance towards the user. Although they pave the way to various interesting applications, it is hard to create virtual bad guys that are taken seriously by the user, since they are typically unable to apply serious sanctions. To address this issue, this study experimentally investigated the effect of “consequential” agents that are able to physically threaten their human interlocutors. A consequential agent was developed by equipping users with a (non-functioning) device, through which they were made to believe the agent could mildly shock them. Effects on participants’ levels of anxiety and (physiological and self-reported) stress were measured, and the role of presence and perceived believability of the virtual agent was assessed. The consequential agent triggered a stronger physiological stress response than the non-consequential agent, whereas self-reported levels of anxiety and stress did not significantly differ. Furthermore, while presence and believability were substantially associated with users’ stress response, both states did not mediate or explain the effect of a consequential vs. non-consequential agent on stress, as they did not significantly differ between conditions. Implications of these findings and suggestions for follow-up studies on “virtual bad guys” are discussed.