Never underestimate the power of social media. Many people get their news directly from social media feeds like Twitter and Facebook. News often breaks on Twitter and the by-the-second updates are often filled with misinformation and outright lies.
Recently, a group of researchers at the University of Sheffield in the United Kingdom and others from all around Europe, began working on a system that would be able to detect lies on social media and thus prevent the spread of false reports. Although some misinformation is completely benign and trivial, false reports made in sensitive and emergency situations can be harmful or even dangerous.
The project was inspired by the 2011 riots in London, during which a lot of lies and rumors flew around social media. Reports that key landmarks were ablaze, that animals had escaped from the zoo and that important buildings were destroyed caused widespread panic and more chaos than was necessary. It also prevented police forces from calming the riots. Such protests are common occurrences all over the world and without accurate information, the situation can quickly escalate. In some cases, a false report can mean the difference between life and death.
Although law enforcement, government and news agencies have all taken to Twitter and other social media platforms in an attempt to clarify misinformation and conform the validity of rumors, it hasn't been enough. While some call for a tightening of restrictions in social media or the complete elimination of these sites, advocates for Internet freedom have different ideas. Neither group has provided a real solution to the problem, so a group of researchers, lead by Kalina Bontcheva, from the University of Sheffield's engineering department, decided to try and find the middle ground.
"There was a suggestion after the 2011 riots that social networks should have been shut down, to prevent the rioters using them to organize," Bontcheva said on BBC. "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 rumors, for example, for the emergency services to quash a lie in order to keep a situation calm."
The researchers invented a program, called Pheme after the Greek goddess of malicious rumors, to root out false reports as they appear on Twitter and other social networks. The program analyzes the information, tests it, finds its source and alerts law enforcement, news and government agencies of the truth behind the rumor, if there is any. That way, journalists, whose job it is to provide the public with truthful and verified information, can do their job better and faster.
In addition to analyzing the words themselves, the program also checks out the person who posted the information to see if they are a reliable source. The program can tell who is a bot, a news organization, a rumor monger, a satirist and who is a liar. It then alerts users of false reports.
The researchers believe that Pheme could save lives and prevent unnecessary violence by simply making it easier to find out the truth.
"People do believe things they hear on the Internet," Bontcheva said. "In critical situations, you can instead show reliable information or alert the authorities before things get out of hand."
Contributors to the project include the Universities of Sheffield, Warwick, King's College London, Saarland in Germany and MODUL University Vienna. Four companies, including ATOS in Spain, iHub in Kenya, Ontotext in Bulgaria and swissinfo.ch are also involved. Pheme is largely funded by the European Union. Those in charge of the project stated that prototypes could be ready in about 18 months.
