Social scientists are increasingly turning to computer-assisted text analysis as a way of understanding the digital footprints left by communities and individuals.  Much of the technology that powers these approaches is borrowed from the fields of computer science and statistics; yet, social scientists have substantially different goals.  We focus on the development of methods that support three core tasks: discovery, measurement and causal inference with text.  We introduce the Structural Topic Model (STM), a bayesian generative model of text which is built for social science inference.  Using this model as a running example, we will discuss the challenges of discovery, measurement and causal inference and how to adapt our tools to approach each task.  The tasks will be illustrated with multiple examples across many different domains.  The talk will end with future directions for this fast-moving, inter-disciplinary field. [Includes joint work with Molly Roberts, Justin Grimmer, Dustin Tingley, Edo Airoldi, Richard Nielsen and others.]