Toward a Virtual Companion for the Elderly: an Investigation on the Interaction between the Attitude and Mood of the Participants during Active Listening

The elderly who live alone are increasing rapidly in these years. For their mental health, it is reported useful to maintain their social life with others. Our project is aiming to develop a companion agent who can engage long-term relationship with the elderly users. This paper presents our first step to explore the rapport occurred in human-human communication which is considered to be essential in keeping social relationship with others. We analyzed the corpus collected in a human-human dyadic conversation experiment from three view points, the speaker (potential user), the listener (the role that the agent will play), and the third person who did not participate the conversation. Encouraging results that may provide the hints of agent development were found in the analysis: the attitude of the conversation can have an influence on the speaker’s mood, the mood of the speaker can be potentially observed by another person, and the third person can detect speaker’s attitude.