sommai - Fotolia

Cardiff University opens Twitter ‘cyberhate’ centre

Cardiff University researchers are to monitor Brexit-related hate crime on Twitter with funding from the Economic and Social Research Council

Cardiff University’s Social Data Science Lab is to open a Centre for Cyberhate Research and Policy to explore and monitor Brexit-related hate crimes on social media and help the government identify areas that require attention, and improve interventions to keep hate crime from spreading online.

The university has been awarded a £250,000 grant by the Economic and Social Research Council to support the work, which will focus on the development of a monitoring tool to display a live feed of the propagation of hate speech on Twitter.

“Hate crimes have been shown to cluster in time and tend to increase, sometimes significantly, in the aftermath of trigger events,” said Matthew Williams, co-director of the Social Data Science Lab, and principal investigator on the project.

“The referendum on the UK’s future in the European Union has galvanised certain prejudiced opinions held by a minority of people, resulting in a spate of hate crimes. Many of these crimes are taking place on social media.

“Over the coming period of uncertainty relating to the form of the UK’s exit, decision makers – particularly those responsible for minimising the risk of social disorder through community reassurance, local policing and online governance – will require near-real-time information on the likelihood of escalation of hateful content spread on social media. This funding will provide the system and evidence needed to achieve this,” said Williams.

The research team will not take a position on Brexit, but merely use it as a demonstration of how a certain trigger can cause a spike in hate speech related to religion, immigration and xenophobia.

Data will be collected from a 12-month period beginning on the date of the European Union (EU) referendum – 23 June 2016 – using machine learning technology to classify, analyse and evaluate tweets in real-time.

Eventually, it hopes to make its tools available to policy-makers and analysts that will show precursors to hate crimes, including the characteristics of social media users; the characteristics of their network, such as accounts followed; the type of hate speech expressed; what content they post; and other external factors, such as media reporting of events.

“We will be enhancing our existing language models using cutting edge computational methods to mine massive amounts of public reaction and provide meaningful insights into hateful and antagonistic commentary in minutes of an event occurring,” said Pete Burnap, computational lead on the project.

Read more about social media

The centre will work closely with the UK head of the Cross-Government Hate Crime Programme and the National Police Chief’s Council, the London Mayor’s Office’s Online Hate Crime Hub, the Metropolitan Police and a number of charities.

Established in 2015, the lab has world-leading expertise on using social media to monitor online crime, and has worked with law enforcement in the UK and the US. It has already carried out preliminary studies of the spread of hate speech after the murder of fusilier Lee Rigby in Woolwich, south London, in 2013.

Read more on Social media technology