This chapter provides an overview of computational text analysis techniques used to study judicial behavior and decision-making. As legal texts become increasingly digitized, scholars can draw on tools from machine learning and natural language processing to convert unstructured texts into quantitative data amenable to empirical analysis. The chapter surveys common methods for representing legal documents and discusses their strengths and weaknesses. Each approach makes tradeoffs between richness of representation and dimensionality reduction. Extracting meaningful data from legal texts requires thoughtful choices about representation and preprocessing. The chapter discusses interpretability, bias, and domain-specific challenges as important considerations when applying text analysis to study courts. Overall, computational text analysis supplements traditional methods and opens new avenues for empirical legal scholarship.