A Computational Apporach to Etiqeutte and Politeness: An "Etiquette Engine™" for Cultural Interaction Training

Keywords: social interaction behavior, etiquette, politeness, culture, NPSs, cross cultural training, training games

Abstract: Computational models and simulations of culture-specific social interactions are useful for a variety of applications including training, interaction or perception prediction and interpretation and even the design of machines and systems which will interact verbally with members of different cultures. To date, such models have been achieved via the scripting of specific trajectories of behaviors or, in limited instances, through very complex, “first principles” psychological models of agent motivation and goal-based behaviors. Neither of these is entirely appropriate for the production of a large series of rich and deep social interactions. We have developed a quantitative, computational implementation of a rich, universal theory of human-human “politeness” behaviors and the culture-specific interpretive frameworks for them (labeled “etiquette”) from sociology, linguistics and anthropology. This model links observable and inferred aspects of power and familiarity relationships, the degree of imposition of an act (each of which have implications for roles and intents) and the actor’s character to produce expectations about politeness behaviors. We have recently demonstrated the ability for this algorithm to produce culture-specific, politeness-appropriate utterances and perceptions of utterances in a game setting. Furthermore, our algorithmic approach to calculating culturespecific attitudes offered distinct advantages over alternate methods of producing such behaviors. Not only was it possible to more rapidly amass a much larger set of alternate trajectories through an interaction setting, but it was also possible to “swap” alternate sets of cultural knowledge to enable giving an agent alternate cultural perceptions with great ease.