Predicting the Law Area and Decisions of French Supreme Court Cases
This work addresses legal prediction for the French Supreme Court, but it is incremental as it applies existing text classification methods to a new dataset.
The paper tackled predicting law area and decisions of French Supreme Court cases using text classification, achieving 96% F1 score for case ruling prediction, 90% for law area prediction, and 75.9% for time span estimation with an SVM classifier.
In this paper, we investigate the application of text classification methods to predict the law area and the decision of cases judged by the French Supreme Court. We also investigate the influence of the time period in which a ruling was made over the textual form of the case description and the extent to which it is necessary to mask the judge's motivation for a ruling to emulate a real-world test scenario. We report results of 96% f1 score in predicting a case ruling, 90% f1 score in predicting the law area of a case, and 75.9% f1 score in estimating the time span when a ruling has been issued using a linear Support Vector Machine (SVM) classifier trained on lexical features.