Attributing Mental States to Non-Embodied Autonomous Systems: A Systematic Review

Rapidly evolving, non-embodied autonomous agents, oftentimes powered by AI, have been shown to trigger mental state attributions by users. However, unlike embodied agents, attributions to non-embodied autonomous agents are not caused by physical presence but by language or abstract interfaces. To better understand this fast-growing field, the present article presents a systematic literature review of mental state attribution to non-embodied autonomous agents. Based on a literature body of 400+ papers, 26 relevant publications were identified, providing an overview of the communities studying mental state attributions, the study’s design choices, and findings of these efforts. The findings indicate that (1) the HCI community is less involved in the study of mental state attributions, (2) a lacking validity of the measures limits the current measurement of mental state attributions, (3) there is a skew towards chat- and voice bots, and (4) mental state attributions increased vulnerabilities of users and shifts in accountability.