Abstract
This paper studies the problem of automated classification of fact statements and value statements in written judicial decisions. We compare a range of methods and demonstrate that the linguistic features of sentences and paragraphs can be used to successfully classify them along this dimension. The Wordscores method by Laver et al. (2003) performs best in held out data. In an application, we show that the value segments of opinions are more informative than fact segments of the ideological direction of U.S. Circuit Court opinions.
Highlights
The contents of court opinions comprise among other things fact statements and value statements
The following value statements, taken from the United States Circuit Court Opinion Database, illustrate the use of modals and attitudes: The principle established has been affirmed by so many decisions in the courts of New Jersey, that it may be considered as the settled law of that state
The results have established that dependency features in the way they are utilized here are useful in identifying linguistic structures that express modalities and propositional attitudes, thereby qualifying them as strong predictors for distinguishing fact and value statements
Summary
The contents of court opinions comprise among other things fact statements and value statements The former concerns what the legal professionals know about the factual grounds of a case, given all evidence available to them. This study uses computational techniques to develop a document classifier that automatically distinguishes between fact and value statements in court opinions. We use a new featural representation of documents based on syntactic dependencies, which captures what linguistically distinguishes fact statements from value statements. As this is exploratory research, we compare a number of models for classifying facts vs values. Future work could use fact-value labels of legal text for many relevant empirical investigations.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
