Researchers analyzing a vast literature on coronaviruses

Washington DC [US], May 21 (ANI): Researchers have created a resource named CoronaCentral that uses machine learning to process and categorize Covid-19 research for the benefit of the scientific community.

In an article titled “Analyzing the Vast Coronavirus Literature with CoronaCentral,” Jake Lever and Russ B. Altman argue that the SARS-CoV-2 pandemic has triggered a surge in research exploring all aspects of the virus and its effects on the virus. human health.

The study published in Proceedings of the National Academy of Sciences of the United States of America (PNAS), shows that the overwhelming publication rate means that researchers are unable to keep abreast of the literature.

According to the researchers, to improve this, the authors presented the CoronaCentral resource which uses machine learning to process the research literature on SARS-CoV-2 with SARS-CoV and MERS-CoV.

“We categorize the literature into useful topics and article types and enable analysis of the content, pace and importance of research during the crisis with the integration of Altmetric data. These topics include therapeutics, disease prediction, as well as growing areas such as “long COVID” and inequality studies. This resource, available at, is updated daily, ”the researchers said.

The COVID-19 pandemic has led to the largest surge of biomedical research on a single subject in documented history. This research is valuable to current and future researchers as they examine the long-term effects of the virus on different aspects of society.

Unfortunately, the vast scale of the literature makes navigation difficult. Machine learning systems capable of automatically identifying topics and article types would be of great benefit to researchers looking for relevant coronavirus research.

“Our approach improves upon existing methods, including LitCovid, by covering a larger number of articles with the inclusion of PubMed and CORD-19 with articles on SARS / MERS, a broader and more specific set of topics, identifying article types (eg, Reviews), integrating Altmetric esteem data, and indexing by a wide range of biomedical terms (eg, drugs, viral lineages, etc.). data is available for download and the full codebase is available on GitHub, ”the authors of the article said.

To provide more detailed and better quality topics, researchers pursue a supervised learning approach and annotated over 3,200 articles with a set of 32 topics and 8 article types. Individual articles can be tagged with multiple topics and usually only one type of article.

Several other topics and article types are identified using simple rules-based methods, including clinical trials and retractions.

As of March 3, 2021, CoronaCentral covered 128,921 articles. (ANI)

About Christopher Rodgers

Check Also

Monica Cheru on Rethinking African Literature

(This is the final interview report with a panel of African writers on August 7. …

Leave a Reply

Your email address will not be published.