Rumour Detection for Social Media
Out researchers are leading a European team that is developing new techniques to distinguish rumour from fact in social media such as Twitter and Facebook. This can be particularly important during major emergencies.
We're leading a global collaboration to create a sophisticated rumour detector for social media.
The unique system will help users verify online rumours as they spread around the globe by classifying in real time whether a piece of information is true or false.
The Pheme project, led by Dr Kalina Bontcheva from our Department of Computer Science, aims to sort online rumours into four types:
- Speculation – such as whether interest rates might rise
- Controversy – as over the MMR vaccine
- Misinformation, where something untrue is spread unwittingly
- Disinformation, where it’s done with malicious intent
In our digital age, rumours - both true and false - spread fast, often with far-reaching consequences. Social networks have been used to allege that Barack Obama was Muslim and claim that the animals were set free from London Zoo during the 2011 riots - both of which were false.
Pheme will help users verify online rumours as they spread around the globe by classifying in real time whether a piece of information is true or false
The pioneering technology will act as tool for journalists, governments, emergency services, health agencies and the private sector to respond more effectively to claims on social media.
The system will also automatically categorise sources to assess their authority, such as news outlets, experts, or automated ‘bots’. It will also look for a history and background, to help spot where Twitter accounts have been created purely to spread false information.
It will search for sources that corroborate or deny the information, and plot how the conversations on social networks evolve. The results will be displayed to the user in a visual dashboard, to enable them to easily see whether a rumour is taking hold.
Dr Kalina Bontcheva said: “We can already handle many of the challenges involved, such as the sheer volume of information in social networks, the speed at which it appears and the variety of forms, from tweets to blog posts. However, it’s currently not possible to automatically analyse, in real time, whether a piece of information is true or false and this is what we’ve now set out to achieve.
“We see the system as a valuable tool to aid human decision making, rather than something that would replace it.”
The three-year EU funded project is a collaboration between five universities – Sheffield, Warwick, King’s College London, Saarland in Germany and MODUL University Vienna in Austria – and four companies – ATOS in Spain, iHub in Kenya, Ontotext in Bulgaria and swissinfo.ch.