Personal Democracy Plus Our premium content network. LEARN MORE You are not logged in. LOG IN NOW >

Building an Automatic "Lie Detector" for Twitter

BY Jessica McKenzie | Thursday, February 20 2014

American inventor Leonarde Keeler testing his lie-detector (Wikipedia/public domain)

An international group of researchers led by the University of Sheffield is building a social media “lie detector” named Pheme, after the mythological rumormonger, that can determine in real time whether a information spread on social media is true or false.

The idea is that identifying misinformation would allow journalists, government agencies, emergency response, health providers and private companies to respond to emergencies and other events more effectively.

“There was a suggestion after the 2011 riots that social networks should have been shut down, to prevent the rioters using them to organise [sic],” says Dr. Kalina Bontcheva, lead researcher on the project. “But social networks also provide useful information – the problem is that it all happens so fast and we can’t quickly sort truth from lies. This makes it difficult to respond to rumours [sic], 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.”

It is unclear from the press release how online rumors might be “quashed”—whether they would be deleted from the platform or merely countered with accurate information. The possibility of deletion conjures up specters of censorship in countries like China and Venezuela, where dissidents are silenced for voicing “rumors.”

Much of the technology to distinguish between truth and falsehood is already there, but the challenge is doing it in real time.

Dr. Bontcheva explains:

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. But 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.

Online rumors will be classified into four groups: speculations, controversy, misinformation (the inadvertent spread of a lie) and disinformation (the intentional spread of a lie).

It will also account for the authority of the source, distinguishing between media outlets, individual journalists, experts or other authority figures, potential eye witnesses and members of the general public.

The Swiss Broadcasting Corporation, swissinfo.ch, one of the project collaborators, will be testing Pheme for use in digital journalism.

Other collaborators include Atos, the Spanish ICT company; iHub, the technology research center in Kenya; and Ontotext, a Bulgarian company that builds core semantic technologies.

Personal Democracy Media is grateful to the Omidyar Network and the UN Foundation for their generous support of techPresident's WeGov section.

For a round-up of our weekly stories, subscribe to the WeGov mailing list.

News Briefs

RSS Feed today >

With Vision of Internet Magna Carta, Web We Want Campaign Aims To Go Beyond Protest Mode

On Saturday, Tim Berners-Lee reiterated his call for an Internet Magna Carta to ensure the independence and openness of the World Wide Web and protection of user privacy. His remarks were part of the opening of the Web We Want Festival at the Southbank Centre in London, which the Web We Want campaign envisioned as only the start of a year long international process underlying his call to formulate concrete visions for the open web of the future, going beyond protests and the usual advocacy groups. GO

First POST: Lifestyles

Google's CEO on "work-life balance"; how CloudFlare just doubled the size of the encrypted web; Dems like Twitter; Reps like Pinterest; and much, much more. GO

monday >

First POST: Showdown

How demonstrators in Hong Kong are using mobile tech to route around government control; will the news penetrate mainland China?; dueling spin from Dems and Reps on which party's tech efforts will matter more in November; and much, much more. GO

friday >

Pirate MEP Crowdsources Internet Policy Questions For Designated EU Commissioners

While the Pirate Party within Germany was facing internal disputes over the last week, the German Pirate Party member in the European Parliament, Julia Reda, is seeking to make the European Commission appointment process more transparent by crowdsourcing questions for the designated Commissioner for Digital Economy & Society and the designated Vice President for the Digital Single Market. GO

First POST: Dogfood

What ethical social networking might look like; can the iPhone promise more privacy?; how Obama did on transparency; and much, much more. GO

thursday >

First POST: Sucks

How the FCC can't communicate; tech is getting more political; Facebook might see a lawsuit for its mood manipulation experiment; and much, much more. GO

wednesday >

First POST: Wartime

A bizarre online marketing effort targets actress Emma Watson; why the news media needs to defend the privacy of its online readers; Chicago's playbook for civic user testing; and much, much more. GO

More