AI Program Predicts The Outcome Of Human Rights Trials With 79 Percent Accuracy


Computer Scientists from the UCL, University of Pennsylvania and the University of Sheffield have created an Artificial Intelligence (AI) program that is capable of predicting the outcome of human rights trials. The AI program was given about 600 cases that were brought before the European Court of Human Rights (ECHR) and was able to predict the outcome of 79% of those cases correctly. This is the first time a method like this is used to predict the outcomes of a major international court. Its creators believe that it will be a useful tool for identifying common patterns in court cases but they are still sure that AI judges will not replace the good old-fashioned human judgment. The study behind the whole concept was published in PeerJ Computer Science.

"We don't see AI replacing judges or lawyers, but we think they'd find it useful for rapidly identifying patterns in cases that lead to certain outcomes. It could also be a valuable tool for highlighting which cases are most likely to be violations of the European Convention on Human Rights," explained Dr Nikolaos Aletras, who led the study at UCL Computer Science.

AI judges aren’t replacing human ones anytime soon

As described in the study the team of researchers found that the judgments made by the ECHR were highly correlated to non-legal facts instead of directly legal arguments. The AI program worked by analyzing descriptions of court cases submitted to the ECHR. The descriptions mentioned included, legal arguments, an outline of the relevant legislation and also a brief history of the case. The machine learning algorithm of the program did the rest of the work.

"The study, which is the first of its kind, corroborates the findings of other empirical work on the determinants of reasoning performed by high level courts. It should be further pursued and refined, through the systematic examination of more data," explained co-author Dr Dimitrios Tsarapatsanis, a Lecturer in Law at the University of Sheffield.


A team of legal and computer scientists from the University of Pennsylvania extracted the information of the cases. That information was published by the ECHR in their publically accessible database.

"Ideally, we'd test and refine our algorithm using the applications made to the court rather than the published judgements, but without access to that data we rely on the court-published summaries of these submissions," explained co-author, Dr Vasileios Lampos, UCL Computer Science.

The identified cases in the English language and then applied an AI algorithm that found patterns in the text. They also chose an equal number of violation and non-violation cases to prevent any bias in the study.


This isn’t the first time outcomes of the court have been predicted but using analysis of the court that was prepared by the court has been used to predict the outcomes for the first time. AI judges aren’t coming anytime soon but the researchers believe that their program can help with the backlog of cases in the ECHR and other places too by highlighting cases which would be a potential violation.

Do let us know your thoughts about this in the comments below.


Image Source 12 and 3