In the nearer future artificial intelligence judges will decide the merits of a case.
An artificial intelligence that predicts the outcome of court proceedings may sound like a futuristic dream.
But a new study claims to have developed an AI that predict the results of human rights trials with 79 per cent accuracy.
The technology is the first to predict the outcomes of major international court trials by analysing case text using a machine learning algorithm, claim the researchers.
The method was devised by researchers at University College London (UCL), the University of Sheffield and the University of Pennsylvania.
'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,' explained Dr Nikolaos Aletras, who led the study at UCL Computer Science.
'It could also be a valuable tool for highlighting which cases are most likely to be violations of the European Convention on Human Rights.'
The researchers found that judgements by the European Court of Human Rights (ECtHR) are highly linked to non-legal facts, rather than directly legal arguments.
This suggests that the judges of the court are, in the jargon of legal theory, 'realists', rather than 'formalists'.
This supports findings from previous studies of the decision-making processes of other high level courts, including the US Supreme Court, says the study.
'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.
The researchers looked at case information by the ECtHR in its public-ally 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 team identified English language data sets for 584 cases relating to Articles 3, 6 and 8* of the European Convention of Human Rights.
They then applied an AI algorithm to find patterns in the text.
To prevent bias and mis-learning, they selected an equal number of violation and non-violation cases to analyse.
The results showed that the most reliable factors for predicting the court's decision were the language used as well as the topics and circumstances mentioned in the case text.
The 'circumstances' section of the text includes information about the factual background to the case.
'Previous studies have predicted outcomes based on the nature of the crime, or the policy position of each judge, so this is the first time judgements have been predicted using analysis of text prepared by the court,' said Dr Lampos.
'We expect this sort of tool would improve efficiencies of high level, in-demand courts, but to become a reality, we need to test it against more articles and the case data submitted to the court'.
The study was published today in the journal PeerJ Computer Science.
0 comments: