Investigating Perceptions of Social Intelligence in Simulated Human-Chatbot Interactions
This addresses the challenge of designing socially intelligent chatbots for conversational interfaces, but it is incremental as it builds on existing research on social intelligence in human-agent interactions.
The study investigated whether human interlocutors can perceive social intelligence dimensions (Authenticity, Clarity, Empathy) in text-based human-chatbot interactions and how this affects interaction quality, finding that people have great difficulty perceiving these elements and that anthropomorphic behavior can be perceived as pleasant or frightening depending on context.
With the ongoing penetration of conversational user interfaces, a better understanding of social and emotional characteristic inherent to dialogue is required. Chatbots in particular face the challenge of conveying human-like behaviour while being restricted to one channel of interaction, i.e., text. The goal of the presented work is thus to investigate whether characteristics of social intelligence embedded in human-chatbot interactions are perceivable by human interlocutors and if yes, whether such influences the experienced interaction quality. Focusing on the social intelligence dimensions Authenticity, Clarity and Empathy, we first used a questionnaire survey evaluating the level of perception in text utterances, and then conducted a Wizard of Oz study to investigate the effects of these utterances in a more interactive setting. Results show that people have great difficulties perceiving elements of social intelligence in text. While on the one hand they find anthropomorphic behaviour pleasant and positive for the naturalness of a dialogue, they may also perceive it as frightening and unsuitable when expressed by an artificial agent in the wrong way or at the wrong time.