UNSTRUCTURED
Global pandemics like COVID-19 put high strain on healthcare systems and health workers around the world, potentially leading to industrial actions from workers. Such events generate plethora of news information published online by news outlets in each country. Processing the information contained in these news articles yields valuable insights on the nature of ongoing events, yet the sheer volume of information to aggregate is out of scope for human experts. To tackle this issue, we leveraged Natural Language Processing (NLP) and built a deep learning system named DeepCovid. DeepCovid is trained on 2.7 million news articles in English from thousands of sources across hundreds of jurisdictions and serves a dual purpose: to find highly relevant news articles, and to summarize the information in them. We validate the design choices behind each component of the system, showing that it achieves both high precision in selection of news articles, and high summarization performance.