Tell me more! Assessing interactions with social robots from speech

Abstract

As social robots are introduced into increasingly more health interventions, one potential area where they might prove valuable is in supporting people's psychological health through conversation. Given the importance of self-disclosure for psychological health, this study assessed the viability of using social robots for eliciting rich disclosures that identify needs and emotional states in human interaction partners. Three within-subjects experiments were conducted with participants interacting with another person, a humanoid social robot, and a disembodied conversational agent (voice assistant). We performed a number of objective evaluations of disclosures to these three agents via speech content and voice analyses, and also probed participants' subjective evaluations of their disclosure to the three agents. Our findings suggest that participants overall disclose more to humans than artificial agents, that agents' embodiment influences disclosure quantity and quality, and that people are generally aware of differences in their personal disclosures to the three agents studied here. Together, the findings set the stage for further investigation into the psychological underpinnings of self-disclosures to robots and their potential role in eliciting disclosures as part of mental and physical health interventions.