Longitudinal Affective Computing Virtual Agents That Respond to User Mood

摘要

We present two empirical studies which examine user mood in long-term interaction with virtual conversational agents. The first study finds evidence for mood as a longitudinal construct independent of momentary affect and demonstrates that mood can be reliably identified by human judges observing user-agent interactions. The second study demonstrates that mood is an important consideration for virtual agents designed to persuade users, by showing that favors are more persuasive than direct requests when users are in negative moods, while direct requests are more persuasive for users in positive moods.