Organizations and individuals increasingly have to deal with large to very large data sets that include spatio-temporal information, such as customer call records, network traffic data, credit card records, wildlife tracking data, and even data from social media such as twitter. We have access to sophisticated statistical and visualization tools for analyzing these data sets. However, the output from these tools is frequently only understandable by experts -- and even experts can start to suffer from information overload. We have designed a system, interactiveX, that guides users to understand the meaning of large spatio-temporal data sets through automatic creation of interactive multimedia explanations that combine text, graphics and the results of data analysis. In this talk, we will first outline the challenges of this task. We will then present the architecture of our system, demonstrate some user interfaces to our system, and describe some recent research results from this work.