[soundcloud url=”https://api.soundcloud.com/tracks/165051736?secret_token=s-YTgYs” params=”color=ff5500&auto_play=false&hide_related=false&show_comments=true&show_user=true&show_reposts=false” width=”100%” height=”166″ iframe=”true” /]
If you aren’t thrilled about the ability to quickly query huge datasets about whatever questions strike your fancy, please listen to this podcast.
This week’s guest, Kalev Leetaru, is the Yahoo Fellow in Residence of International Values, Communications Technology & the Global Internet at the Institute for the Study of Diplomacy in the Edmund A. Walsh School of Foreign Service at Georgetown University. Phew. More to the point, Leetaru is pushing the Global Database of Events, Languages, and Tones. Also known as GDELT, this project has taken more than 250 million historical data points from the past 35 years to try to determine patterns between, say, the current unrest in Ukraine and historical events.
If the past is prologue, this is a pretty fabulous tool to have at your disposal. Which it now is, since Google has made the dataset available via its cloud platform. Leetaru is clearly jazzed about the possibilities here — being able to fire off questions fast and furious against a huge data set is certainly a change from the not-so-distant past when you had to queue up for access to government- owned supercomputers. And wait.
Now, with huge datasets and the compute power to crunch them readily available, it’s hard not to catch his enthusiasm. What’s truly exciting about this is the ability even lay researchers have to follow up on tangents that crop up during their work. Those forays might end up being wild goose chases. Or result in valuable insights. You can’t know until you pursue them. And GDELT now enables that pursuit.
Hosts: Barb Darrow and Derrick Harris