Effects of Emotional Expressiveness on Voice Chatbot Interactions

Abstract

Speech-based dialog systems primarily interact with users through their spoken responses. Understanding users’ perception of, and subconscious behaviors toward, the system’s speech are crucial for improving their design. In the current study, a voice chatbot designed for having a conversation with users in the domain of music is used to test the impact of emotional expressiveness in its text-to-speech (TTS) output. We parametrically manipulated the degree of emotional expressiveness via prosody and lexical choice across conditions. We used a two-pronged approach to test these effects on users: a user interaction study (Experiment 1 – between-subjects design) and an independent perception study (Experiment 2 – within-subjects design). Both studies provide converging evidence that increasing emotional prosody yields more positive perceptions of chatbot interactions, in increasing perception of emotional expressiveness (Experiments 1 and 2) as well as overall engagement, human-likeness, and likability of the bot (Experiment 2). We discuss these findings in terms of theories of human-computer interaction, as well as their implications for conversational design.