Machine Learning Tool Could Provide Unexpected Scientific Insights into COVID-19

Recently, members of the Ceder Group have been part of a team of materials scientists at Lawrence Berkeley National Laboratory (Berkeley Lab) who have built a text-mining tool in record time to help the global scientific community synthesize the mountain of scientific literature on COVID-19 being generated every day. The tool, live at covidscholar.org, which contains a continuously updated database of cleaned and searchable papers (including preprint papers), uses natural language processing techniques to not only quickly scan and search tens of thousands of research papers, but also help draw insights and connections that may otherwise not be apparent.

COVIDScholar was developed in response to a March 16 call to action from the White House Office of Science and Technology Policy that asked artificial intelligence experts to develop new data and text mining techniques to help find answers to key questions about COVID-19.

(Adapted from an LBL article written by Julie Chao. Read the original article, containing more details and quotes from group members here: Machine Learning Tool Could Provide Unexpected Scientific Insights into COVID-19)