You are here

Predicting Judicial Decisions: A Statistically Rigorous Approach and a New Ensemble Classifier


Andrea Visentin, Alessia Nardotto, Barry O'Sullivan

Publication Type: 
Edited Conference Meeting Proceeding
Natural language processing and machine learning are gaining wide popularity in supporting judicial decision-making. Research in this area is particularly active. However, a methodological issue in the use of AI methods can lead to poor statistical soundness in the results. We consider and improve the work of Aletras et. al.for predicting the outcome of cases at the European Court of Human Rights. We replicate their experiments using a more statistically reliable methodology and analyzed the results using state-of-the-art Bayesian techniques for classifier comparison. We also improved classification accuracy using an ensemble-based approach. These techniques will widely improve the statistical soundness of machine learning applications in law by providing robust baselines for comparison.
Conference Name: 
I31st International Conference on Tools with Artificial Intelligence
Digital Object Identifer (DOI):
Publication Date: 
Conference Location: 
United States of America
National University of Ireland, Cork (UCC)
Open access repository: