Texting with humanlike conversational agents: Designing for anthropomorphism

Conversational agents (CAs) are natural language user interfaces that emulate human-to-human communication. Because of this emulation, research into CAs is inseparably linked to questions about anthropomorphism—the attribution of human qualities, including consciousness, intentions, and emotions, to nonhuman agents. Past research has demonstrated that anthropomorphism affects human perception and behavior in human-computer interactions, for example by increasing trust and connectedness or stimulating social response behavior. Based on the psychological theory of anthropomorphism and related research on computer interface design, we develop a theoretical framework for designing anthropomorphic CAs. We identify three groups of factors to stimulate anthropomorphism: technology design-related, task-related, and individual factors. Our findings from an online-experiment support the derived framework but also reveal novel, yet counterintuitive, insights. In particular, we demonstrate that not all combinations of anthropomorphic technology design cues increase perceived anthropomorphism. For example, we find that using only nonverbal cues harms anthropomorphism; however, this effect turns positive when nonverbal cues are complemented with verbal or human identity cues. We also find that whether CAs complete computer-like or human-like tasks and individuals’ disposition to anthropomorphize greatly affect perceived anthropomorphism. This work advances our understanding of anthropomorphism and makes the theory of anthropomorphism applicable to our discipline. We advise on the direction research and practice should take to find the right spot in anthropomorphic CA design