Interactive surfaces are increasingly common in museums and other informal learning environments where they are seen as a medium for promoting social engagement. However, despite their increasing prevalence, we know very little about factors that contribute to collaboration and learning around interactive surfaces. In this paper we present analyses of visitor engagement around several multi-touch tabletop science exhibits. Observations of 629 visitors were collected through two widely used techniques: video study and shadowing. We make four contributions: 1) we present an algorithm for identifying groups within a dynamic flow of visitors through an exhibit hall; 2) we present measures of group-level engagement along with methods for statistically analyzing these measures; 3) we assess the effect of observational techniques on visitors' engagement, demonstrating that consented video studies do not necessarily reflect visitor behavior in more naturalistic circumstances; and 4) we present an analysis showing that groups of two, groups with both children and adults, and groups that take turns spend longer at the exhibits and engage more with scientific concepts.

In this paper we present a qualitative analysis of natural history museum visitor interaction around a multi-touch tabletop exhibit called DeepTree that we designed around concepts of evolution and common descent. DeepTree combines several large scientific datasets and an innovative visualization technique to display a phylogenetic tree of life consisting of over 70,000 species. After describing our design, we present a study involving pairs of children interacting with DeepTree in two natural history museums. Our analysis focuses on two questions. First, how do dyads negotiate their moment-to-moment exploration of the exhibit? Second, how do dyads develop and negotiate their understanding of evolutionary concepts? In order to address these questions we present an analytical framework that describes dyads’ exploration along two dimensions: coordination and target of action. This framework reveals four distinct patterns of interaction, which, we argue, are relevant for similar interactive designs. We conclude with a discussion of the role of design in helping visitors make sense of interactive experiences involving the visualization of large scientific datasets.