Computer experts from five European universities to collaborate on Pheme authenticity program.
New software in development will analyse the truthfulness of 140 character Twitter posts in a move to stop malicious rumours circulating around the social network. The Pheme program is backed by EU funding and is named after the Greek mythological personification of fame, will aim to asses the honesty of tweets and seek out Twitter accounts set up to spread false information.
Speaking on the issue lead researcher Dr Kalina Bontcheva from the University of Sheffield notes that the spread of information is so fast on Twitter that, ‘"This makes it difficult to respond to rumours, for example, for the emergency services to quash a lie in order to keep a situation calm. Our system aims to help with that, by tracking and verifying information in real time.”
To verify a tweet’s reliability the Pheme system will look at the level of authority a post has, for example a press release compared to post from a member of the public. It will then go onto look at the authenticity of the account itself before searching the web for other stories that confirm or deny the post.
The system sets out to then separate information into four categories: speculation, controversy, misinformation - where a lie has been circulated unknowingly and disinformation, where an out-and-out lie has been deliberately posted.
Pheme will be able to draw from current search technologies, Bontcheva went on to state, “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 videos, pictures and blog posts”. Bontcheva speculates working prototypes may be ready before 18 months.
The system will be tested by Swiss Broadcasting Corporation journalists and members of the Institute of Psychiatry at King's College London with researchers from Sheffield and Warwick universities in the UK, Saaland in Germany and MODUL in Austria.