Abstract
The growth of social media and on-line social networks has opened up a set of fascinating new challenges and directions for researchers in both computing and the social sciences, and an active interface is growing between these areas. We discuss a set of basic questions that arise in the design and analysis of systems supporting on-line social interactions, focusing on two main issues: the role of network structure in the dynamics of social media sites, and the analysis of textual data as a way to study properties of on-line social interaction. Overview The study of on-line social interaction has provided a wide range of insights into the dynamics of social phenomena, the flow of information through the world, and the design of systems supporting the collective creation and sharing of content. Two broad recent themes in the analysis of these domains have been the use of network methods for reasoning about the patterns of interaction [Jackson, 2008; Easley and Kleinberg, 2010; Newman, 2010] and the use of text and language analysis for reasoning about the content itself [Manning et al., 2008; Pang and Lee, 2008]. A promising direction is to bring these two collections of methods together, combining the analysis of what is being communicated in these systems with the structural patterns that characterize the communication. Research over the past several years has begun to explore such a synthesis for several different kinds of phenomena, including the inference of power and status in social interactions [Bramsen et al., 2011; Gilbert, 2012; Otterbacher and Hemphill, 2012]; identification of different roles in these interactions [Diehl et al., 20De Choudhury et al., 2010]; analysis of how content is shaped in political contexts [Conover et al., 2011; Livne et al., 2011]; and investigations of how content enters news coverage and popular discourse [Leskovec et al., 2009; Simmons et al., 2011; Danescu-Niculescu-Mizil et al., 2012a; 2012b]. Here we consider three lines of work that contribute to this combined analysis of structure and content. We begin by discussing the question of textual memes that spread online [Leskovec et al., 2009; Simmons et al., 2011], and the