February 20, 2014
Social Media Rumors To Be Assessed Using Online Lie Detector
[ Watch the Video: Detecting Lies Online ]
Lawrence LeBlond for redOrbit.com - Your Universe Online
Rumors have been a staple of society for nearly as long as humans have been speaking. But with the advent of the Internet and social media, rumors have spread like wildfire. And whether true or false, rumors do spread fast, often with far-reaching consequences.
Now, a team of researchers led by the University of Sheffield is looking to develop a new system that can automatically determine if rumors are true or false as they spread around the world. Such a system could enable those who need the information most, such as journalists, governments and emergency services, to enact response efforts more effectively.
Some of the biggest rumors that spread like wildfire due to social media in recent years were accusations that Kenyan elections were rigged, allegations that Barack Obama was Muslim and claims that animals were released from the London Zoo during the 2011 riots.
“There was a suggestion after the 2011 riots that social networks should have been shut down, to prevent the rioters using them to organize,” lead researcher Dr. Kalina Bontcheva, of the Department of Computer Science at Sheffield’s Faculty of Engineering, said in a statement.
“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, 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,” Dr. Bontcheva added.
The project, which has been funded by the European Union, aims to classify online rumors into four types: speculation, controversy, misinformation and disinformation.
The system, which is being touted as an online lie detector, would automatically categorize sources to assess their authority, such as news outlets, individual journalists, experts, eye-witnesses, public informants or automated “bots.” The system will also look for history and background to determine if the source is trustworthy. For example, many Twitter accounts have been created for the sole purpose of spreading false information.
The system will also search for sources that either corroborate or deny the rumors and plot how the rumors evolve over social media to help determine authenticity of the information. Search results will be displayed to the user in a visual dashboard to enable them to see whether a rumor is true, false and/or taking hold among the online social community.
“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,” said Dr. Bontcheva.
The project will be constantly evaluated via two real-world domains. For the digital journalism aspect, it will be tested by swissinfo.ch, the online arm of the Swiss Broadcasting Corporation. For healthcare, it will be tested by the Institute of Psychiatry at King’s College London.
The project, called Pheme, is expected to last three years and is a collaboration of five universities – Sheffield, Warwick, KCL, Saarland in Germany and MODUL University Vienna. Four companies have also signed on to the project: ATOS in Spain, iHub in Kenya, Ontotext in Bulgaria and swissinfo.ch.
According to Sheffield, Pheme was a person of interest in Greek mythology. She was said to have “pried into the affairs of mortals and gods, then repeated what she learned, starting off at first with just a dull whisper, but repeating it louder each time, until everyone knew.” Pheme is described as the “personification of fame and notoriety, her favour being notability, her wrath being scandalous rumours.”