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.”
Go deeper with Bing News on:
Detecting false stories
- Doubts raised over rapid Covid tests in plan for English care home visitson November 30, 2020 at 10:58 am
A flagship government scheme to use rapid testing to allow care home visitors to hug loved ones before Christmas has been dealt a serious blow after a council instructed providers not to use the tests ...
- Coronavirus | RT-LAMP: a new technology for detecting COVID-19on November 28, 2020 at 7:47 am
The novel coronavirus, SARS-CoV-2, causes the Coronavirus disease-2019 (COVID-19) and this pandemic. It is highly infective, and everyday thousands of people are newly infected. Since there is no ...
- Detecting Fraud: What Are Weak Signals and How to Process Themon November 23, 2020 at 2:58 pm
Certain companies, specifically organizations with the wrong tone at the top, improper incentives, confusing cash flow trends, and siloed departments, are more susceptible to fraud than others. Pick ...
- US approves first self-testing kit for detecting Covid-19on November 17, 2020 at 11:33 pm
The Food and Drug Administration issued an emergency use authorization to Lucira Health Inc.’s rapid-result All-In-One Test Kit, according to a statement from the government agency Tuesday.
- T-cell test EIGHT TIMES better at detecting past coronavirus infectionon November 12, 2020 at 11:10 am
New research from the manufacturer, Adaptive Biotechnologies, which is based in Seattle, found that the test was eight times better at detecting past COVID-19 infection than a commercially ...
Go deeper with Google Headlines on:
Detecting false stories
Go deeper with Bing News on:
Detecting fake news
- Cyber attack puts finance industry on edgeon November 27, 2020 at 5:03 am
The collapse of a hedge fund has shone the light on a financial services industry unprepared for the rise in hacking and cyber crime across Australia.
- The $500,000 Cost of Not Detecting Good vs. Bad Bot Behavioron November 25, 2020 at 4:56 am
Bot attacks caused financial harm to 80% of eCommerce businesses, according to new research. Read more results, and how bot protection is evolving in response ...
- BI nabs two Koreans with fake marriage travel paperson November 23, 2020 at 10:50 pm
Bureau of Immigration (BI) officers at the Ninoy Aquino International Airport (NAIA) intercepted over the weekend two Koreans who entered the country by using fake entry visas and pretending to be ...
- What Your Fraud Detection Vendor Misseson November 23, 2020 at 5:59 am
There are many other forms of fraud impacting display and video ads purchased through programmatic channels, that are not bots hitting webpages.
- Review: Group-IB Fraud Hunting Platformon November 18, 2020 at 5:02 am
Aside from detecting anomalous use of a service ... related to user reputation (e.g., boosting reputation as a fake seller on e-commerce sites). The platform also enables service owners to ...