Controlling the Gaze of Conversational Agents

We report on a pilot experiment that investigated the effects of different eye gaze behaviours of a cartoon-like talking face on the quality of human-agent dialogues. We compared a version of the talking face that roughly implements some patterns of human-like behaviour with two other versions. In one of the other versions the shifts in gaze were kept minimal and in the other version the shifts would occur randomly. The talking face has a number of restrictions. There is no speech recognition, so questions and replies have to be typed in by the users of the systems. Despite this restriction we found that participants that conversed with the agent that behaved according to the human-like patterns appreciated the agent better than participants that conversed with the other agents. Conversations with the optimal version also proceeded more efficiently. Participants needed less time to complete their task