Effects of conversational agents on human communication in thought-evoking multi-party dialogues

Abstract

This paper presents an experimental study that analyzes how conversational agents activate human communication in thought-evoking multi-party dialogues between multi-users and multi-agents. A thought-evoking dialogue, which is a kind of interaction in which agents act on user willingness to provoke user thinking, has the potential to stimulate multi-party interaction. In this paper, we focus on quiz-style multi-party dialogues between two users and two agents as an example of a thought-evoking multi-party dialogue. The experiment results showed that the presence of a peer agent significantly improved user satisfaction and increased the number of user utterances. We also found that agent empathic expressions significantly improved user satisfaction, raised user ratings of a peer agent, and increased user utterances. Our findings will be useful for stimulating multi-party communication in various applications such as educational agents and community facilitators.