Nonverbal communication is an essential component of our daily life. A quick eyebrow frown from a student will inform the teacher of possible confusion. A tilt of the head may show doubt during negotiation.The goal of this project is to study how to computationally represent the temporal dynamics of nonverbal behaviors. Our approach is to include prior knowledge about nonverbal communication, both specific to the domain (e.g., nonverbal behaviors related to psychosis disorders) and also generic based on the large prior literature on discourse and conversational analysis. This research will allow for reliable measurement of similarity and variability between nonverbal behaviors.