Read an article the other day on the analysis of the Arab Spring (Did the Arab Spring really spark a wave of global protests, in Foreign Policy) using a Google Ideas sponsored project, the GDELT Project (Global Database of Events, Language and Tone) file of events extracted from worldwide media sources. The GDELT database uses sophisticated language processing to extract “event” data from news media streams and supplies this information in database form. The database can be analyzed to identify trends in world events and possibly to better understand what led up to events that occur on our planet.
The GDELT database records over 300 categories of events that are geo-referenced to city/mountaintop and time-referenced. The event data dates back to 1979. The GDELT data captures 60 attributes of any event that occurs, generating a giant spreadsheet of event information with location, time, parties, and myriad other attributes all identified, and cross-referenceable.
Besides the extensive spreadsheet of world event attribute data the GDELT project also supplies a knowledge graph oriented view of its event data. The GDELT knowledge graph “compiles a list of every person, organization, company, location and over 230 themes and emotions from every news report” that can then be used to create network diagrams/graphs to be better able to visualize interactions between events.
For example see the Global Conversation in Foreign Policy, for a network diagram of every person mentioned in the news during 6 months of 2013. You can zoom in or out to see how people identified in news reports are connected during the six months. So if you we’re interested, in let’s say the Syrian civil war, one could easily see at a glance any news item that mentioned Syria or was located in Syria since 1979 to now. Wow!
Arab Spring and Worldwide Protest
Getting back to the chart-of-the-month, the graphic above shows the “protest intensity” by month for the last 30 years with a running average charted in black using GDELT data. (It’s better seen in the FP article/link above or just click on it for an expanded view. ).
One can see from the chart that there was a significant increase in protest activity after January 2011, which corresponds to the beginning of the Arab Spring. But the amazing inference from the chart above is that this increase has continued ever since. This shows that the Arab Spring has had a lasting contribution that has significantly increased worldwide protest activity.
This is just one example of the types of research available with the GDELT data.
I have talked in the past about how (telecom, social media and other) organizations should deposit their corporate/interaction data sets in some public repository for the better good of humanity so that any researcher could use it (see my Data of the world, lay down your chains post for more on this). The GDELT Project is Google Ideas doing this on a larger scale than I ever thought feasible. Way to go.
Image credits: (c) 2014 ForeignPolicy.com, All Rights Reserved