Answers are grounded in this paper and cite their sources.
In this paper we describe the design of a relational agent interface for handheld computers and the results of a study exploring the effectiveness of different user-agent interaction modalities. Four different agent output modalities-text only, static image plus text, animated, and animated plus nonverbal speech-are compared and their impact on the ability of the agent to establish a social bond with the user, the perceived credibility of information delivered, and user acceptance is evaluated. Subjects ranked the two animated versions of the system higher on all measures.
No takes yet. Share an insight, caveat, or question.
Bickmore et al. (2006) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: