Analyses of student data in post-secondary education should be sensitive to the fact that there are many different topics of study. These different areas will interest different kinds of students, and entail different experiences and learning activities. However, it can be challenging to identify the distinct academic themes that students might pursue in higher education, where students commonly have the freedom to sample from thousands of courses in dozens of degree programs. In this paper, we describe the use of topic modeling to identify distinct themes of study and classify students according their observed course enrollments, and present possible applications of this technique for the broader field of educational data mining. [For the full proceedings, see ED593090.]