COVID-19 Insight Tools

Data Science Tools and Exploration of the Kaggle Covid-19 Open Research Dataset Challenge (CORD-19).


This site delivers a suite of tools that enable exploration of and deliver insights from the
Kaggle CORD-19 Challenge CORD-19 is a resource of over 51,000 scholarly articles,
including over 40,000 with full text, about COVID-19, SARS-CoV-2, and related coronaviruses.

Go to Applications

Applications

OpenIE Extractor

Extract relations from sentences in the form of triples

Knowledge Graph

Find relations in the text with SPARQL queries

Kibana

Create new visualizations and dashboards

FacetSearch

Free text search and faceted filtering

Climateview

Explore relation between climate and Covid-19

COVID19 Visualization

Explore individual US states COVID19 response

OpenIE Extractor

This is a rest endpoint for creating OpenIE Triples extractions. "The Open IE system runs over sentences and creates extractions that represent relations in text. There are many binary relations in a sentence that can be expressed as a triple (A, B, C) where A and B are arguments, and C is the relation between those arguments. Since Open IE is not aligned with an ontology, the relation is a phrase of text." Input your own sentence and extract triples that can be used to build your own knowledge graph.


Knowledge Graph

This knowledge graph is built on top of the OpenIE triples extractions. Additionally, instances of clinical and biomolecular entities have been tagged in the text, allowing the user to query for relations and entities. You can post SPARQL queries to the graph. For a list of prefixes of the resource mappings and predicates see the documentation Example queries can be found here


Kibana

Create your own visualizations and dashboards of CORD-19 using Kibana.


FacetSearch

Free text search of the full CORD-19 corpus. Filter and facet on various aspects of the data such as journal, publication date, mentions of named entities such as Genes, Proteins, Anatomical Sites, etc. Named entities were extracted from the text using Apache cTakes and SciSpacy Named Entity Recognition models.

ClimateView

The COVID-19 severity map portrays the correlation between weather and the severity of the COVID-19 pandemic across various locations in the world. The colouring of the locations depicts the Koppen-Geiger climate zone (starting from polar climates and ending with tropical/megathermal climates). The green markers within each of those locations depict the severity of COVID-19, calculated using the deaths, cases, total number of mentions, number of papers that mention the location, as well as number of times death is mentioned alongside that location in a paper. Explore the interactive map.

US Covid19 Visualization

Explore a visualization showing data from the United States Covid Tracking Project Monitor state by state how social distancing and stay at home orders impacted COVID-19 growth and how "flattening the curve" is going in each state

.