‘CoronaCheck’ website combats spread of misinformation

Cornell University
2-Apr-2020 3:00 PM EDT, by Cornell University

Newswise — ITHACA, N.Y. - Cornell University researchers have developed an automated system that uses machine learning, data analysis and human feedback to automatically verify statistical claims about the new coronavirus.

“CoronaCheck,” based on ongoing research from Immanuel Trummer, assistant professor of computer science, launched internationally in March and has already been used more than 9,600 times. The database – now available in English, French and Italian – checks claims on COVID-19’s spread based on reliable sources such as the World Health Organization and the Centers for Disease Control and Prevention.

“There’s way too much misinformation about the coronavirus on the web – it’s pretty mind-boggling, actually,” Trummer said. “Some of these misinformation claims are harmless, but others – things like ‘eating silver cures the coronavirus’ – can be dangerous.”

The CoronaCheck system is a collaboration between Trummer’s team, including doctoral students Georgios Karagiannis and Saehan Jo, and Paolo Papotti’s team at Eurecom, an engineering school in Biot, France.

Because of the sheer volume of bad information on the internet – and the rate at which more misinformation is produced and spread – it’s impossible for humans to resolve the problem by performing manual fact checks alone. Even common automated approaches, which generally attempt to map new claims to existing fact checks, can’t be realistically conducted on a scale large enough to tackle misinformation’s scope, Trummer said.

“We’ve tried to automate the entire process, from the raw data to the text that we want to verify,” Trummer said.

CoronaCheck adapts “Scrutinizer,” a system Trummer developed with Eurecom for the International Energy Agency in Paris, a nongovernmental organization, to support human fact checkers in translating text summaries into equations the computer can understand and solve. To do this, Scrutinizer employs machine learning and natural language processing – a branch of artificial intelligence aimed at deciphering human language – as well as large datasets that help the system figure out how to approach each new claim, and feedback from human users.

“Computers have a hard time understanding natural language,” he said. “We cannot directly ask the computer to check whether some claim in a sentence is correct or not. So we essentially have to translate the claim from our language into a query language the computer understands.”

For example, if someone types in that the number of coronavirus cases is higher in France than in Italy, the system uses a kind of elimination process to narrow down the possible equations to represent that text. It draws on its datasets to create a mathematical expression that can compare the claim to the facts.

Then, based on experience, the system determines the best sources to verify the claim, drawing on reliable public data compiled daily by Johns Hopkins University. The system’s machine learning model can also improve over time, learning to recognize new claim types based on user feedback.

“There’s a tremendous amount of misinformation out there and the set of claims that people check for is quite diverse,” Trummer said. “For any given claim, there is a very large number of possible query expressions, and our goal is to find the right one.”

The database interface builds on Trummer’s related work, including AggChecker, the first tool to automatically verify text summaries of datasets by querying a relational database. AggChecker was presented at the Association for Computing Machinery’s Special Interest Group on Management of Data’s annual conference in 2019.

His team has also developed an “Anti-Knowledge Base” of common factual mistakes from Wikipedia in collaboration with Google NYC. The research behind CoronaCheck was partly funded by a Google Faculty Research Award.

Filters close

Showing results

110 of 1958
Released: 27-May-2020 7:55 PM EDT
Models for Incorporating Non-Pharmaceutical Interventions
Society for Risk Analysis (SRA)

To help answer major questions about COVID19, governments have been reaching out to epidemiologists, medical practitioners and others who have some expertise in disease modeling in order to better understand the trajectory of the virus and its impact on society. One of the most widely used models are called Mathematical Compartmental Models, which simplify the mathematical modeling of infectious diseases.

Released: 27-May-2020 5:30 PM EDT
To Prevent a Second Wave of COVID-19, AACC Calls on Senate to Include 5 Recommendations in Upcoming Coronavirus Bill
American Association for Clinical Chemistry (AACC)

Now that the latest coronavirus relief package, known as the Heroes Act, has moved forward to the U.S. Senate, AACC has sent a letter to Senate leadership outlining five key recommendations that will improve COVID-19 testing capacity across the U.S. AACC urges the Senate to ensure these recommendations are addressed within the Heroes Act, as they are critical to preventing a second wave of the pandemic.

Newswise: Researchers use ALCF resources to model the spread of COVID-19
Released: 27-May-2020 5:05 PM EDT
Researchers use ALCF resources to model the spread of COVID-19
Argonne National Laboratory

Argonne researchers lead highly detailed COVID-19 modeling efforts to understand how the virus spreads through populations.

Released: 27-May-2020 5:05 PM EDT
Exploring the Zoonotic Origins of COVID-19
Society for Risk Analysis (SRA)

Around the start of the COVID-19 pandemic, there was a lot of dialog surrounding its zoonotic origins, or its transmission from animals to humans. A new study explores how zoonotic origins are communicated can influence risk perception and preventative behaviors, including how people interact with animals that are known to be possible sources of a disease.

Newswise: Pediatric scoring scale helps surgeons decide whether to operate during COVID-19 delays
Released: 27-May-2020 3:40 PM EDT
Pediatric scoring scale helps surgeons decide whether to operate during COVID-19 delays
American College of Surgeons (ACS)

Pediatric surgeons have modified an evaluation tool for use in pediatric patients that allows surgeons to prioritize operations during COVID-19.

Newswise: Hackensack Meridian Health Joins #FitForTheFrontLine Challenge with Nation’s Top Medical and Academic Centers in Support of Frontline Health Care Workers
Released: 27-May-2020 3:05 PM EDT
Hackensack Meridian Health Joins #FitForTheFrontLine Challenge with Nation’s Top Medical and Academic Centers in Support of Frontline Health Care Workers
Hackensack Meridian Health

Hackensack Meridian Health is joining medical centers across the United States to start a country-wide movement of physical activity to honor and support frontline health care workers who have worked tirelessly to save lives. Spearheaded by Mount Sinai Health System, #FitForTheFrontLine is a national fitness challenge which began on Tuesday, May 26, and ends on Sunday, June 14 (Flag Day). The event encourages Americans young and old to move, exercise and get fit to increase awareness and raise funds to support our nation’s health care heroes.

Newswise: The Pandemic’s Byproduct: Work-Life Integration, At Last
Released: 27-May-2020 3:05 PM EDT
The Pandemic’s Byproduct: Work-Life Integration, At Last
The Society of Thoracic Surgeons

Dr. Mara B. Antonoff shares how working from home and virtual meetings have improved her work-life balance and advocates for keeping some of these protocols in place after the COVID-19 pandemic subsides.

Released: 27-May-2020 2:40 PM EDT
Drastic Changes in Social Lives Raise Future Mental Health Concerns
University of Texas at Austin (UT Austin)

People’s social lives aren’t what they used to be. But exactly how they’ve changed and what it might mean for mental health is what psycho-linguistic researchers at The University of Texas at Austin are trying to figure out in the Pandemic Project.

Showing results

110 of 1958