Anti-Polish hate crimes to be tackled by AI

Artificial intelligence is being used to tackle hate speech against Polish people on social media after a rise in online abuse.

Hatelab, based at Cardiff University, and Samurai Labs, a Polish company, are using the technology to monitor aggressive social media content.

There were more than 94,000 hate crimes recorded in England and Wales in 2017-18 – up 17% on the previous year.

More than 900,000 Polish people live in the UK.

Studies by Samurai Labs found 5% of material published about Polish people on social media had negative or offensive connotations.

Cardiff University said the artificial intelligence could “accurately differentiate between web aggression and harmless comments”.

Samurai Labs chief executive Michal Wroczynski said the AI could detect eight categories of abuse, from people being told to go home to threats to life.

Matthew Williams, director of Hatelab, claimed the technology was important because of an increase in hate speech since the 2016 EU referendum.

He said: “As the United Kingdom prepares to leave the European Union, using the most advanced methods of artificial intelligence is going to be vital in helping the authorities to quickly recognise warning signs and provide reassurance and security to the Polish community living here.”