Contemporary dictionary-based approaches to sentiment analysis exhibit serious validity problems when applied to specialized vocabularies, but human-coded dictionaries for such applications are often labor-intensive and inefficient to develop. We demonstrate the validity of “minimally-supervised” approaches for the creation of a sentiment dictionary from a corpus of text drawn from a specialized vocabulary. We demonstrate the validity of this approach in estimating sentiment from texts in a large-scale benchmarking dataset recently introduced in computational linguistics, and demonstrate the improvements in accuracy of our approach over well-known standard (nonspecialized) sentiment dictionaries. Finally, we show the usefulness of our approach in an application to the specialized language used in US federal appellate court decisions.

While Supreme Court cases are generally salient or important, some are many degrees more important than others. A wide range of theoretical and empirical work throughout the study of judicial politics implicates this varying salience. Some work considers salience a variable to be explained, perhaps with judicial behavior the explanatory factor. The currently dominant measure of salience is the existence of newspaper coverage of a decision, but decisions themselves are an act of judicial politics. Because this coverage measure is affected only after a decision is announced, using it limits the types of inferences we can draw about salience. We develop a measure of latent salience, one that builds on existing work, but that also explicitly incorporates and models predecision information. This measure has the potential to ameliorate concerns of causal inference, put research findings on sounder footing, and add to our understanding of judicial behavior.

The Institutional Grammar (IG) is used to analyse the syntactic structure of statements constituting institutions (e.g., policies, regulations, and norms) that indicate behavioural constraints and parameterize features of institutionally governed domains. Policy and administration scholars have made considerable progress in methodologically developing the IG, offering increasingly clear guidelines for IG‐based coding, identifying unique considerations for applying the IG to different types of institutions, and expanding its syntactic scope. However, while validated as a robust institutional analysis approach, the resource and time commitment associated with its application has precipitated concerns over whether the IG might ever enjoy widespread use. Needed now in the methodological development of the IG are reliable and accessible (i.e., open source) approaches that reduce the costs associated with its application. We propose an automated approach leveraging computational text analysis and natural language processing. We then present results from an evaluation in the context of food system regulations.

Although racial bias in the law is widely recognized, it remains unclear how these biases are in entrenched in the language of the law, judicial opinions. In this article, we build on recent research introducing an approach to measuring the presence of implicit racial bias in large-scale corpora. Utilizing an original dataset of more than one million appellate court opinions from US state and federal courts, we estimate word embeddings for the more than 400,000 most common words found in legal opinions. In a series of analyses, we find strong and consistent evidence of implicit racial bias, as African-American names are more frequently associated with unpleasant or negative concepts, whereas European-American names are more frequently associated with pleasant or positive concepts. The results have stark implications for work on the neutrality of the legal system as well as for our understanding of the entrenchment of bias through the law.

When the Supreme Court takes action, it establishes national policy within an issue area. A traditional, legal view holds that the decisions of the Court settle questions of law and thereby close the door on future litigation, reducing the need for future attention to that issue. Alternatively, an emerging interest group perspective suggests the Court, in deciding cases, provides signals that encourage additional attention to particular issues. I examine these competing perspectives of what happens in the federal courts after Supreme Court decisions. My results indicate that while Supreme Court decisions generally settle areas of law in terms of overall litigation rates, they also introduce new information that leads to increases in the attention of judges and interest groups to those particular issues.