Analyzing the vast coronavirus literature with CoronaCentral

Area of Science:

• Virology
• Public Health
• Computational Biology

Background:

• The COVID-19 pandemic triggered an unprecedented volume of scientific publications.
• Keeping up with the rapidly expanding SARS-CoV-2 research literature is a significant challenge for scientists.
• Existing literature search tools may not adequately capture the breadth and depth of pandemic-related research.

Purpose of the Study:

• To introduce CoronaCentral, a machine learning-powered resource for processing and analyzing the scientific literature on SARS-CoV-2, SARS-CoV, and MERS-CoV.
• To enable researchers to monitor the content, pace, and focus of research during the pandemic.
• To provide a categorized overview of key research areas, including therapeutics, forecasting, long COVID, and health inequalities.

Main Methods:

• Utilized machine learning algorithms to process a large corpus of scientific literature related to coronaviruses.
• Categorized research articles into relevant topics and types.
• Integrated Altmetric data to analyze research impact and trends.
• Developed a web-based resource for daily updates and analysis.

Main Results:

• CoronaCentral categorizes literature into key topics such as therapeutics, disease forecasting, long COVID, and health inequality.
• The resource allows for the analysis of research trends and emphasis over time.
• Daily updates ensure the information remains current amidst rapid publication rates.
• Altmetric data integration provides insights into research dissemination and impact.

Conclusions:

• CoronaCentral offers a valuable solution for researchers overwhelmed by the volume of COVID-19 literature.
• The resource facilitates a deeper understanding of research trends and priorities during the pandemic.
• By organizing and analyzing coronavirus research, CoronaCentral supports informed scientific inquiry and public health strategies.