Behaviors and Perceptions of Human-Chatbot Interactions Based on Top Active Users of a Commercial Social Chatbot

DOI

Natural language processing is enabling machines to communicate with humans naturally, yet the dynamics of extended user-chatbot interactions remain much unexplored. This study characterizes the conversational styles, demographics, psychologies, and emotional tendencies of the most active users (i.e., top 1\% by message count) of a commercial chatbot platform (SimSimi.com), whom we refer to as \textit{superusers}. We analyze the linguistic patterns and topics of 1,988,971 messages by 1,994 superusers written over a period of three years. We further surveyed 76 users to observe their emotional dispositions and perceptions towards the chatbot. We find that superusers of SimSimi empathize and humanize the chatbot more than less active users and show higher tendency to share personal and negative feelings. Our finding suggests that chatbots need new design considerations for users who are vulnerable due to their high anthropomorphism and openness toward machines. Our work also shows that chatbots should have functions to offer social support when necessary.