Effects of Conversational Agents on Human Communication in Thought-Evoking Multi-Party Dialogues

Kohji Dohsaka, Ryota Asai, Ryuichiro Higashinaka, Yasuhiro Minami and Eisaku Maeda

SIGDIAL Workshop on Discourse and Dialogue (SIGDIAL 2009)
Queen Mary University of London, September 11-12, 2009


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 is a kind of interaction in which agents act on users' willingness to provoke their own thinking, and it has 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 and user positive ratings of the agents, and further increased user utterances. Our findings will be useful for stimulating multi-party communication in various applications such as educational agents and community facilitators.