Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.
Who will be affected?
Readers: No access to all 28 journals. We recommend accessing our articles via PubMed Central
Authors: No access to the submission form or your user account.
Reviewers: No access to your user account. Please download manuscripts you are reviewing for offline reading before Wednesday, July 01, 2020 at 7:00 PM.
Editors: No access to your user account to assign reviewers or make decisions.
Copyeditors: No access to user account. Please download manuscripts you are copyediting before Wednesday, July 01, 2020 at 7:00 PM.
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Targeted COVID-19 and Human Resource for Health News Information Extraction with a Multi-Component Deep Learning Framework
Mathieu Ravaut;
Ruochen Zhao;
Duy Phung;
Vicky Mengqi Qin;
Dusan Milovanovic;
Johannes Schnitzler;
Anita Pienkowska;
Iva Bojic;
Josip Car;
Shafiq Joty
ABSTRACT
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.
Citation
Please cite as:
Ravaut M, Zhao R, Phung D, Qin VM, Milovanovic D, Schnitzler J, Pienkowska A, Bojic I, Car J, Joty S
Targeting COVID-19 and Human Resources for Health News Information Extraction: Algorithm Development and Validation