Skip to main contentSkip to navigationSkip to navigation
Computer keyboard
The algorithm examined English language data sets for 584 cases relating to torture and degrading treatment, fair trials and privacy. Photograph: Cultura/Rex/Shutterstock
The algorithm examined English language data sets for 584 cases relating to torture and degrading treatment, fair trials and privacy. Photograph: Cultura/Rex/Shutterstock

Artificial intelligence 'judge' developed by UCL computer scientists

This article is more than 7 years old

Software program can weigh up legal evidence and moral questions of right and wrong to predict the outcome of trials

Artificial intelligence software that can find patterns in highly complex decisions

is being used to predict our taste in films, TV shows and music with ever-increasing accuracy. And now, after a breakthrough study by a group of British scientists, it could be used to predict the outcome of trials.

Software that is able to weigh up legal evidence and moral questions of right and wrong has been devised by computer scientists at University College London, and used to accurately predict the result in hundreds of real life cases.

The AI “judge” has reached the same verdicts as judges at the European court of humanrights in almost four in five cases involving torture, degrading treatment and privacy.

The algorithm examined English language data sets for 584 cases relating to torture and degrading treatment, fair trials and privacy. In each case, the software analysed the information and made its own judicial decision. In 79% of those assessed, the AI verdict was the same as the one delivered by the court.

Dr Nikolaos Aletras, the lead researcher from UCL’s department of computer science, said: “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.” An equal number of “violation” and “non-violation” cases were chosen for the study.

The artificial intelligence algorithm reached the same verdict as judges at the European court of human rights in almost four of five cases. Photograph: Frederick Florin/AFP/Getty Images

In the course of developing the programme the team found that judgments of the European court of human rights depends more on non-legal facts than purely legal arguments.

This suggests that the court’s judges are more legal theory “realists” than “formalists”. The same is true of other high level courts, such as the US supreme court, according to previous studies.

The most reliable factors for predicting European court of human rights decisions were found to be the language used as well as the topics and circumstances mentioned in the case texts.

The study’s co-author, Dr Dimitrios Tsarapatsanis, a law lecturer from Sheffield university, where Aletras completed his doctorate, said the study was the first of its kind.

It corroborated the findings of other research on the factors that influenced the judgments of high level courts, he said. “It should be further pursued and refined through the systematic examination of more data.”

Dr Vasileios Lampos, a UCL computer scientist, added: “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 judgments have been predicted using analysis of text prepared by the court.

“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.”

Lawyers are increasingly making use of software that can perform complex tasks – such as searching for concepts rather than simple keywords – which can greatly reduce the amount of time needed to determine what documents might be relevant to a case, for example.

For the time being, however, Judge Judy – or Judge Rinder, for that matter – may not need to think about retraining just yet.

The findings by Aletras and his colleagues were published in the journal PeerJ Computer Science.

Comments (…)

Sign in or create your Guardian account to join the discussion

Most viewed

Most viewed