The ASReview team developed a plugin for researchers and doctors to facilitate the reading of literature on the Corona-virus. The plugin makes the CORD-19 dataset available in the ASReview software. We also constructed a second database with studies published after December 1st 2019 to search for relevant papers published during the Covid-19 crisis.

The CORD-19 dataset

The CORD-19 dataset is made available through a collaboration of the Allen Institute for AI, the Chan Zuckerberg Initiative, Georgetown University’s Center for Security and Emerging Technology, Microsoft Research, and the National Library of Medicine of the National Institutes of Health.

Version 5 of the dataset (csv, dated March 27, 2020) contains metadata of 45.8K publications on COVID-19 and coronavirus-related research (e.g. SARS, MERS, etc.) from PubMed Central, the WHO COVID-19 database of publications, the preprint servers bioRxiv and medRxiv and papers contributed by specific publishers (currently Elsevier).

Two versions of the CORD-19 dataset (publications relating to COVID-19) are made available in ASReview: the full dataset and a dataset with publications from December 2019 onwards. The CORD-19 dataset is updated weekly. The modified datasets described here will be updated shortly after. The current datasets are based on CORD-19 version 5 (released 2020-03-27)

ASReview

The Active learning for Systematic Reviews (ASReview) software implements learning algorithms that interactively query the researcher during the title/abstract phase of a systematic search. This way of interactive training is known as Active Learning. ASReview offers support for classical learning algorithms and state-of-the-art learning algorithms like neural networks. The software can be used for classical systematic reviews for which the user uploads a dataset of papers, or one can make use of the built-in datasets.