via University of Waterloo
A new artificial intelligence (AI) tool could help social media networks and news organizations weed out false stories.
The tool, developed by researchers at the University of Waterloo, uses deep-learning AI algorithms to determine if claims made in posts or stories are supported by other posts and stories on the same subject.
“If they are, great, it’s probably a real story,” said Alexander Wong, a professor of systems design engineering at Waterloo. “But if most of the other material isn’t supportive, it’s a strong indication you’re dealing with fake news.”
Researchers were motivated to develop the tool by the proliferation of online posts and news stories that are fabricated to deceive or mislead readers, typically for political or economic gain.
Their system advances ongoing efforts to develop fully automated technology capable of detecting fake news by achieving 90 per cent accuracy in a key area of research known as stance detection.
Given a claim in one post or story and other posts and stories on the same subject that have been collected for comparison, the system can correctly determine if they support it or not nine out of 10 times.
That is a new benchmark for accuracy by researchers using a large dataset created for a 2017 scientific competition called the Fake News Challenge.
While scientists around the world continue to work towards a fully automated system, the Waterloo technology could be used as a screening tool by human fact-checkers at social media and news organizations.
“It augments their capabilities and flags information that doesn’t look quite right for verification,” said Wong, a founding member of the Waterloo Artificial Intelligence Institute. “It isn’t designed to replace people, but to help them fact-check faster and more reliably.”
AI algorithms at the heart of the system were shown tens of thousands of claims paired with stories that either supported or didn’t support them. Over time, the system learned to determine support or non-support itself when shown new claim-story pairs.
“We need to empower journalists to uncover truth and keep us informed,” said Chris Dulhanty, a graduate student who led the project. “This represents one effort in a larger body of work to mitigate the spread of disinformation.”
Learn more: New tool uses AI to flag fake news for media fact-checkers
Go deeper with Bing News on:
Detecting false stories
- Standardization of the liquid biopsy for pediatric diffuse midline glioma using ddPCRon March 3, 2021 at 11:43 pm
Diffuse midline glioma (DMG) is a highly morbid pediatric brain tumor. Up to 80% of DMGs harbor mutations in histone H3-encoding genes, associated with poor prognosis. We previously showed the ...
- Pentagon Report Assessed Lasers and Radar to Detect 'Deception'on March 2, 2021 at 11:08 am
It’s almost impossible to tell when humans are lying and the technology we use to do so is based on pseudoscience and bad research.
- Application Security Backsliding, Over 70% of Organizations Say Their Portfolio Is More Vulnerableon March 2, 2021 at 6:12 am
Ponemon and WhiteSource report on application security indicates that most large enterprise-scale organizations feel that their portfolio of applications has become more vulnerable recently.
- St. Pölten UAS Graduate Develops Fake News Detectoron March 2, 2021 at 5:26 am
Detecting Fake News AutomaticallyST. PÖLTEN, Austria, March 2, 2021 /PRNewswire/ -- Armin Kirchknopf, a graduate of the degree programme ...
- Researchers confirm a threshold value for non-invasive imaging biomarkeron March 1, 2021 at 9:36 pm
Breast cancer is the commonest fatal cancer in women. Early detection increases a woman's chances of recovery. Magnetic Resonance Imaging (MRI) is an accurate technique for detecting and classifying ...
Go deeper with Google Headlines on:
Detecting false stories
Go deeper with Bing News on:
Detecting fake news
- Hacked SendGrid accounts used in phishing attacks to steal loginson March 4, 2021 at 8:44 am
A phishing campaign targeting users of Outlook Web Access and Office 365 services collected thousands of credentials relying on trusted domains such as SendGrid.
- Royal Mail issues scam warning to UK customers over unpaid fee texts circulatingon March 3, 2021 at 1:20 pm
ROYAL MAIL has warned Britons of the new scams that are currently circulating. The postal company regularly updates its scam advice online - here are the latest ones customers should look out for.
- French tax office trials social media checks to detect fraudon March 3, 2021 at 12:36 pm
French tax authorities will now be able to use data published online to cross-check tax declarations. This includes text, images, videos and photos published on social media sites such as Facebook, ...
- Human instinct can be as useful as algorithms in detecting online 'deception'on March 2, 2021 at 9:04 am
Travelers looking to book a hotel should trust their gut instinct when it comes to online reviews rather than relying on computer algorithms to weed out the fake ones, a new study suggests.
- St. Pölten UAS Graduate Develops Fake News Detectoron March 2, 2021 at 5:26 am
Detecting Fake News AutomaticallyST. PÖLTEN, Austria, March 2, 2021 /PRNewswire/ -- Armin Kirchknopf, a graduate of the degree programme ...
