Computer Algorithm correctly predicts outcomes of human rights cases


Pic: Thinkstock. Nico El Nino

It sounds like something from a science fiction movie, but software developed at University College London (UCL) has been used to successfully predict the outcome of 4 in 5 complex cases put before the European Court of Human Rights.

The Artificial Intelligence method, developed jointly with the University of Sheffield and the University of Pennsylvania uses a machine learning algorithm to predict decisions and has proved to be 79% accurate.

“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.

The Algorithm can recognise patterns in highly complex decisions and the development team found that judgements by the ECtHR are very strongly correlated to non-legal facts rather than directly legal arguments.

They identified English language data sets, available from the court, for 584 cases relating to Articles 3, 6 and 8 of the Convention on Human Rights, and applied an AI algorithm to find patterns in the text. To prevent bias and mislearning, they selected an equal number of violation and non-violation cases.

Although the system would not be used to make judgements, it is expected that the AI ‘judge’ could help courts that are under heavy demand, improve their level of efficiency.

Related Articles

Playing Spectrum Sino