The data sets were derived from coronavirus related scientific literature using the CORD-19 dataset released by the Allen Institute of Artificial Intelligence as of July 14, 2020, using the Elasticsearch engine hosted by the Digital Scholarship Center (DSC). Through indexing the full-text and the metadata of the article corpus, the research team generated a full-corpus model and 7 different models corresponding to key viral outbreaks from the past several decades' coronaviruses (SARS-CoV, MERS-CoV, and SARS- CoV-2) and non-coronaviruses (HIV, Zika, H1N1, and Ebola). The targeted subsets of the articles used two or more occurrences of virus-specific keywords drawn from conventions established by the World Health Organization.
