How this AI tool tracks spread, evolution of COVID-19 conspiracy theories on social media


Los Alamos (N.M.) National Laboratory researchers created a machine learning algorithm that identifies COVID-19 related conspiracy theories on social media and shows how they evolve over time, according to an April 19 news release.

For the study, published April 14 in the Journal of Medical Internet Research, the researchers used publicly available, anonymous Twitter data to characterize four COVID-19 conspiracy theory themes and provide context for each through the first five months of the pandemic.

The four themes the study analyzed were: that 5G cell towers spread the COVID-19 virus; the Bill and Melinda Gates Foundation engineered COVID-19; the virus was developed in a laboratory; and that the COVID-19 vaccines, which were still in development during the time of the research, would be dangerous.

"We began with a dataset of approximately 1.8 million tweets that contained COVID-19 keywords or were from health-related Twitter accounts," said Dax Gerts, a computer scientist at Los Alamos, said in the news release. "From this body of data, we identified subsets that matched the four conspiracy theories using pattern filtering, and hand labeled several hundred tweets in each conspiracy theory category to construct training sets."

The research team used the data collected for each of the four theories to build the machine learning models, which can categorize tweets as COVID-19 misinformation or not. The researchers found that misinformation tweets contained more negative sentiment when compared to factual tweets and that conspiracy theories evolved over time.


© Copyright ASC COMMUNICATIONS 2021. Interested in LINKING to or REPRINTING this content? View our policies by clicking here.


Featured Whitepapers

Featured Webinars