Politeness and alignment in dialogues with a virtual guide

Abstract

Language alignment is something that happens automatically in dialogues between human speakers. The ability to align is expected to increase the believability of virtual dialogue agents. In this paper we extend the notion of alignment to affective language use, describing a model for dynamically adapting the linguistic style of a virtual agent to the level of politeness and formality detected in the user's utterances. The model has been implemented in the Virtual Guide, an embodied conversational agent giving directions in a virtual environment. Evaluation shows that our formality model needs improvement, but that the politeness tactics used by the Guide are mostly interpreted as intended, and that the alignment to the user's language is noticeable.