Research that assesses individual judges’ ability to shape decisions typically focuses on courts that publish separate votes and opinions. Yet, many courts issue per curiam judgments that do not permit public dissent. To overcome this limitation, we use a convolutional neural network (CNN) to model the variation in judges’ expressed preferences from language in aggregated judgments. Specifically, we construct a CNN to analyze the written judgments of judge-rapporteurs and opinions of advocates-general from the Court of Justice of the European Union. Along a pro-/anti-EU dimension, we estimate how judgments differ within (1) each case relative to the advocate-general’s opinion, and (2) each judge-rapporteur, which captures how judges alter their writing across cases. Our results provide novel empirical support for theoretical models of European judicial decision-making: more pro-EU opinions driven by the Court, not the advocate-general or the judge-rapporteur, are associated with larger chambers and stronger external signals of compliance.

Institutional designers of judiciaries often want to provide the appearance of impartiality. As a result, many collegial courts issue per curiam rulings in which judges’ votes are not public. An extensive scholarship, however, provides evidence that ideology and mechanisms of retention affect judicial decision-making. Do per curiam rulings actively mitigate or provide cover for ideological and career-oriented judicial decision-making? I argue that – when serving as the rapporteur (opinion-writer) – a judge on a civil law per curiam court can steer their panel towards the outcome their appointer prefers. When their appointing government turns over, nonetheless, a judge is not compelled to change their decision-making to be in line with their new government, as per curiam rulings protect them from retaliation. An analysis of decisions at the Court of Justice of the European Union provides evidence for this account.