Researchers working on social media 'lie detector'

Updated 29 April 2014
0

Researchers working on social media 'lie detector'

LONDON: University researchers are working on a system that could quash rumors spreading on social media by identifying whether information is accurate.
Five European universities, led by Sheffield in northern England, are cooperating on a system that could automatically identify whether a rumor originates from a reliable source and can be verified.
The researchers said Tuesday they hope the system will allow governments, emergency services, media and the private sector to respond more effectively to claims emerging and spreading on social media before they get out of hand.
The three-year, European Union-funded project, called PHEME, is an attempt to filter out the nuggets of factual information from the avalanche of ill-informed comment on Twitter and Facebook.
"Social networks are rife with lies and deception," the project leaders said in a statement. Such messages can have far-reaching consequences, but there is so much of it that it is impossible to analyse it in real time.
Claims during the 2011 riots in London that the London Eye observation wheel was on fire or that all the animals were let out of London Zoo were given as examples of false rumors that spread rapidly via the Internet.
The research is being led by Dr Kalina Bontcheva of Sheffield University's Faculty of Engineering.
"The problem is that it all happens so fast and we can't quickly sort truth from lies," she said.
"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. Our system aims to help with that, by tracking and verifying information in real time."
The project is trying to identify four types of information -- speculation, controversy, misinformation, and disinformation -- and model their spread on social networks.
It will try to use three factors to establish veracity: the information itself (lexical, syntactic and semantic); cross-referencing with trustworthy data sources; and the information's diffusion.
The results can be displayed to the user on screen.
"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," said Bontcheva.
"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."
The Times newspaper said the EU would meet most of the predicted 4.3 million euros costs of the project and a final version is hoped for within 18 months.
The project is a collaboration between five universities -- Sheffield, King's College London, Warwick in England, Saarland in Germany and MODUL University Vienna -- and four companies - ATOS in Spain, iHub in Kenya, Ontotext in Bulgaria and swissinfo.ch.
rjm/gj/er


Internet traffic hijack disrupts Google services

In this Monday, Nov. 5, 2018, photo, a woman carries a fire extinguisher past the logo for Google at the China International Import Expo in Shanghai. Internet traffic hijacking disrupted several Google services Monday, Nov. 12, 2018, including search and cloud-hosting services. (AP)
Updated 13 November 2018
0

Internet traffic hijack disrupts Google services

  • Google confirmed Monday’s disruption on a network status page but said only that it believed the cause was “external to Google”

CALIFORNIA: An Internet diversion that rerouted data traffic through Russia and China disrupted several Google services on Monday, including search and cloud-hosting services.
Service interruptions lasted for nearly two hours and ended about 5:30 p.m. EST., network service companies said. In addition to Russian and Chinese telecommunications companies, a Nigerian Internet provider was also involved.
Google confirmed Monday’s disruption on a network status page but said only that it believed the cause was “external to Google.” The company had little additional comment.
The specific method employed, formally known as border gateway protocol hijacking, can knock essential services offline and facilitate espionage and financial theft. Most network traffic to Google services — 94 percent as of October 27 — is encrypted, which shields it from prying eyes even if diverted.
Alex Henthorn-Iwane, an executive at the network-intelligence company ThousandEyes, called Monday’s incident the worst affecting Google that his company has seen.
He said he suspected nation-state involvement because the traffic was effectively landing at state-run China Telecom. A recent study by US Naval War College and Tel Aviv University scholars says China systematically hijacks and diverts US Internet traffic.
Much of the Internet’s underpinnings are built on trust, a relic of the good intentions its designers assumed of users. One consequence: little can be done if a nation-state or someone with access to a major Internet provider decides to reroute traffic.
Henthorn-Iwane says Monday’s hijacking may have been “a war-game experiment.”
In two recent cases, such rerouting has affected financial sites. In April 2017, one affected Mastercard and Visa among other sites. This past April, another hijacking enabled cryptocurrency theft .
The Department of Homeland Security did not immediately respond to a request for comment.
ThousandEyes named the companies involved in Monday’s incident, in addition to China Telecom, as the Russian Internet provider Transtelecom and the Nigerian ISP MainOne.