Scientists and clinicians have responded to the rapid spread of COVID-19, by generating new research materials. This has given rise to two unique challenges. One, it is humanly impossible for scientists and clinicians to review the vast amount of new research on time. Two, there is no way to establish the quality of these preprint materials as they have not undergone peer-review.
Scientists and clinicians have responded to the rapid spread of COVID-19, by generating new research materials. This has given rise to two unique challenges. One, it is humanly impossible for scientists and clinicians to review the vast amount of new research on time. Two, there is no way to establish the quality of these preprint materials as they have not undergone peer-review.
Consequently, a group of five Illinois Computer Science (CS) professors dedicated themselves to finding answers to these challenges. They have come up with PaperBoat, an Artificial Intelligence (AI) enabled knowledge discovery framework, which they believe will accelerate scientific discovery.
Inspiration regarding COVID-19 specifically struck this group after monitoring research outlets like PubMed 1 following the outbreak in December. PubMed 1 produces about 300 new papers on a given day. Even before the outbreak, the rate at which new research appeared exceeded an individual’s capacity to review it. Since December, a simple keyword search for “coronavirus” results in about 125 new papers published every day.
To simplify scientific discovery, PaperRobot first finds and collects all the knowledge on a certain topic by focusing on the text of the research papers. Subsequently, it produces a knowledge graph that shows how the elements within this topic interact with each other. Besides, PaperRobot develops a link prediction, which scours the research available to see if previously unconnected subjects have a hidden connection. Finally, it uses graph mining to review conflicting or complimentary information to produce hypothesis verification or even generate a new hypothesis.
The influx of research covering COVID-19 makes it even harder for individuals from different communities to find the right counterpart. In this scenario, PaperBoat provides the best collaborative network possible. Besides, for COVID-19, it can offer an infrastructure that can help the research community collaborate and accelerate the scientific discovery process.
Click here to read the original article published by Illinois Computer Science.
Please give your feedback on this article or share a similar story for publishing by clicking here.
