Covid-on-the-Web: Knowledge Graph and Services to Advance COVID-19 Research

Franck Michel (1, 2) , Fabien Gandon (1, 2) , Valentin Ah-Kane (1, 2) , Anna Bobasheva (1, 2) , Elena Cabrio (1, 2) , Olivier Corby (1, 2) , Raphaël Gazzotti (1, 2) , Alain Giboin (1, 2) , Santiago Marro (1, 2) , Tobias Mayer (1, 2) , Mathieu Simon (3) , Serena Villata (1, 2) , Marco Winckler (1, 2)

1 WIMMICS - Web-Instrumented Man-Machine Interactions, Communities and Semantics
2 Laboratoire I3S - SPARKS - Scalable and Pervasive softwARe and Knowledge Systems
3 Inria Rennes – Bretagne Atlantique

Scientists are harnessing their multidisciplinary expertise and resources to fight the COVID-19 pandemic. Aligned with this mind-set, the Covid-on-the-Web project aims to allow biomedical researchers to access, query and make sense of COVID-19 related literature. To do so, it adapts, combines and extends tools to process, analyze and enrich the "COVID-19 Open Research Dataset" (CORD-19) that gathers 50,000+ full-text scientific articles related to the coronaviruses. We report on the RDF dataset and software resources produced in this project by leveraging skills in knowledge representation, text, data and argument mining, as well as data visualization and exploration. The dataset comprises two main knowledge graphs describing (1) named entities mentioned in the CORD-19 corpus and linked to DBpedia, Wikidata and other BioPortal vocabularies, and (2) arguments extracted using ACTA, a tool automating the extraction and visualization of argumentative graphs, meant to help clinicians analyze clinical trials and make decisions. On top of this dataset, we provide several visualization and exploration tools based on the Corese Semantic Web platform, MGExplorer visualization library, as well as the Jupyter Notebook technology. All along this initiative, we have been engaged in discussions with healthcare and medical research institutes to align our approach with the actual needs of the biomedical community, and we have paid particular attention to comply with the open and reproducible science goals, and the FAIR principles.

Mots clés: COVID-19; arguments; visualization; named entities; linked data

Domaines: Intelligence artificielle [cs.AI]

Franck Michel, Fabien Gandon, Valentin Ah-Kane, Anna Bobasheva, Elena Cabrio, et al.. Covid-on-the-Web: Knowledge Graph and Services to Advance COVID-19 Research. ISWC 2020 - 19th International Semantic Web Conference, Nov 2020, Athens / Virtual, Greece. ⟨10.1007/978-3-030-62466-8_19⟩. ⟨hal-02939363⟩