GDELT: Big Data of News, Conflicts, and Society
What is happening in this world today? Obviously, it is impossible for us to read and analyze billions of news reports published every day. GDELT is designed to record, analyze, visualize and even forecast our planet.
By Ran Bi, Sep 2014
Built by Kalev Leetaru, a Georgetown University researcher, the Global Database of Events, Language, and Tone (GDELT) Project is the largest open-access database on human society in existence. Event Database includes physical activities from 1979 and Global Knowledge Graph is a massive network connecting every person, organization, company and location over the world.
Supported by Google Ideas, the GDELT Project monitors the world’s broadcast, print, and web news from nearly every corner of every country in over 100 languages and identifies the people, locations, organizations, counts, themes, sources, and events driving our global society every second of every day, creating a free open platform for computing on the entire world.
What can we do with these data? Take a look at GDELT’s Global Material conflict 48-hour Trend and World Leaders Index. These reports are released everyday and may give you an idea. From yesterday (Sep. 29)’s report, India (corruption) and Hong Kong (demonstrators) are the keywords of material conflict.
Play with GDELT – Google BigQuery
To play with GDELT, you can download the whole dataset and analyze it on your machine. However, the exciting news is that GDELT is available in Google BigQuery, which enables near-realtime adhoc querying over the entire database.
BigQuery is simple using SQL query and super fast. Currently it can be used for free within certain quotas. I tested its sample query on BigQuery, which discovered the top defining relationships by scanning 250 million records detailing worldwide events from the last 30 years.
It is truly impressive to understand our planet in such an intuitive way. More GDELT projects can be found here. From what I have seen so far, GDELT would be a good start to do political science research.