The 'Etiquette Quotient': An Approach to Believable Social Interaction Behaviors

摘要

Making avatars react appropriately in social interaction - to take offense when reasonable, to give deference where appropriate, etc. - is a more fundamental need for believability and cost-effectiveness than is accuracy in appearance, especially for applications where complex and realistic interactions with intelligent agents are important - such as cross-cultural training for military personnel. We are using a rich, universal theory of human-human "politeness" behaviors and the culture-specific interpretive frameworks for them (labeled "etiquette") from sociology, linguistics and anthropology to create a computational model of social behavior expectations. This model links observable and inferred aspects of power and familiarity relationships, the degree of imposition of an act (all of which have implications for roles and intents) and the actor's character to produce expectations about politeness behaviors. By using observations of politeness behaviors (or their lack), the same model permits inferences and updates about those attributes. We are refining and implementing this model to provide a computational believability metric based on the delta between observed and expected politeness behaviors - an "Etiquette Quotient" (EQ) - of an actor in context. We see applicability of this model to interactive avatar behavior generation and adaptation through modular, cross-cultural etiquette libraries.