In keeping with this year’s ICMI theme about multimodal interaction and its role in society, this workshop is aimed at analysing group dynamics by bringing together fundamental and applied settings. Recently, in the fields of social signal processing and affective computing, there has been a trend to move from controlled lab experiments to perception of group phenomena in uncontrolled real life settings, leading to significant technical challenges. This implies a great need to gather more data to train, validate, and test methods for behaviour perception, modelling, and synthesis. To capture temporal group and team dynamics, both social and computer scientists are increasingly working with annotated behavioral interaction data. Such data can provide the basis for developing novel research lines that capture dynamic, often "messy" group phenomena and at the same time provide intriguing challenges for the automated analysis of multimodal interaction. For example, what can the behavioral patterns of social signals in group interactions tell us about complex, often difficult to grasp emergent group constructs such as conflict, cohesion, cooperation, or team climate? Technological advances in social signal processing allow for novel ways of group analysis to tackle these types of questions. At the same time, a growing number of group researchers with a background in the social sciences are embracing more behavioral approaches to group phenomena. Facilitating dialogue collaboration among these disciplines has the potential to spark synergies and radically innovate both research in multimodal interaction research as well as group research. This workshop is part of a timeline of initiatives starting from a 2016 Lorentz Workshop which aimed to bring group scholars and researchers in the social and affective computing community together. The strong belief is that there is a lot to gain from both sides from meeting, discussing ideas, and working together. This effort is a continuation of effort to bring more group researchers and computer scientists together by providing a meeting point to encourage more collaboration.