Global Database of Events, Language and Tone (GDELT)

With specific application to disaster reporting

Description: The GDELT Project is a realtime network diagram and database of global human society for open research.

The Global Database of Events, Language and Tone (GDELT) project publishes data on broadcast, print and web news articles. The GDELT data contain information automatically extracted from online news media around the world. Supported by Google Jigsaw, the project uses advanced machine learning techniques and text analysis of these news articles to identify various items such as events, themes or topics, number of mentions, or tone of text.

GDELT Event Database

The GDELT Event Database records over 300 categories of physical activities around the world, from riots and protests to peace appeals and diplomatic exchanges, georeferenced to the city or mountaintop, across the entire planet dating back to January 1, 1979 and updated every 15 minutes.

GDELT Visual Global Knowledge Graph

Worldwide news reporting is increasingly saturated by imagery, but historically GDELT has been limited to the textual contents of global journalism. As of January 2016, a random sample of up to a million images a day are drawn from the media of almost every country and processed through Google's Vision API.

Website: https://www.gdeltproject.org/