India-led team develops online research system to curb COVID-19 misinformation
Toronto: A team led by an Indian-born researcher in Canada has developed a new system that increases the accuracy and reliability of health-related online research by 80% to help people make better decisions on topics such as COVID-19.
The team at the University of Waterloo in Canada noted that Internet search engines are the most common tools the public uses to research facts about COVID-19 and its effects on their health.
A proliferation of disinformation can have real consequences, which is why the team has created a way to make this research more reliable.
“With so much new information coming out all the time, it can be difficult for people to know what is true and what is not,” said Ronak Pradeep, doctoral student at the Cheriton School of Computer Science in Waterloo. and principal author of a study.
“But the consequences of misinformation can be quite serious, like people going out and buying drugs or using home remedies that can hurt them,” Pradeep said.
The researchers said that even the big search engines that host billions of searches every day cannot keep up because there has been so much scientific data and research on COVID-19 in such a short time.
“Most systems are trained on well-organized data, so they don’t always know how to tell the difference between an article promoting the use of bleach to prevent COVID-19 versus real information on health, ”Pradeep said.
“Our goal is to help people see the right articles and get the right information so that they can make better decisions in general with things like COVID,” he added.
Pradeep said the project aims to refine internet research agendas to promote the best health information for users.
The team took advantage of its two-step neural reclassification architecture for research, which they supplemented with a tag prediction system trained to distinguish correct information from questionable and incorrect information.
The system is linked to a research protocol that draws on World Health Organization (WHO) data and verified information as the basis for ranking, promoting and sometimes even excluding articles online.
“Our design has the potential to improve consumer health research to combat misinformation, a challenge recently amplified by the COVID-19 pandemic,” the study authors wrote.
Pradeep and other authors Xueguang Ma, Rodrigo Nogueira and Jimmy Lin, University of Waterloo, presented a paper on the preliminary results of the system at SIGIR ’21, a conference on research and development in information retrieval , held July 11-15. in line.