This paper exploits a relatively new approach to quantitative text analysis — topic modeling — to examine the subject matter of Supreme Court decisions, and in particular to analyze how the semantic content produced by the Court differs from the published decisions of the U.S. Appellate Courts. To conduct this analysis, we fit a topic model to the joint corpus of decisions (Supreme Court plus Appellate Court). The topic model enables a quantitative measurement of differences in semantic content between three corpora: the Supreme Court decisions, the Appellate Court decisions, and Appellate Court cases selected for review. We develop new methods to estimate these differences over time. We reach two findings. First, the Supreme Court has become substantially more semantically idiosyncratic in recent decades, as measured by the use of the topic distribution within a decision as a predictor of the authoring court. We then examine potential causes of this trend, isolating the use of the Court’s case selection power. We find that the topic model based measure of semantic difference between the cases selected for review by the Court does not appear to be increasing over time, indicating instead that the Court has become more distinctive in how it discusses a similarly distinct pool of cases. Normative implications and avenues for future research are discussed. This work demonstrates the utility of topic modeling as a valuable supplement to and/or replacement of hand-coded labels in the study of hierarchically arranged judiciaries. While this case study focuses on the U. S. Courts, extensions and broadening to other national and international judicial corpora can be readily accomplished. More generally, this work opens the door for broader application of topic models within empirical legal studies and related disciplines to study the rich textual corpora generated by legal institutions.
Stored only when both papers are in the corpus — 5 citations exist upstream.
Imported from OpenAlex (CC0) — nothing here is generated.