Its always incredibly exciting to see all of the different ways that GDELT is being applied and it is especially compelling to see some of the incredibly sophisticated analytic techniques that are being applied to GDELT that take advantage of its unique size, scale, and richness.
This year's International Social Computing, Behavioral-Cultural Modeling and Prediction Conference (SBP 2014) featured GDELT for its Grand Data Challenge. The winning submission, titled "Bayesian dynamic financial networks with time-varying predictors" applied "a Bayesian nonparametric model including time-varying predictors in dynamic network inference … to infer the dependence structure among financial markets during the global financial crisis, estimating effects of verbal and material cooperation efforts … [learning] contagion effects with increasing influence of verbal relations during the financial crisis and opposite results during the United States housing bubble."
The paper made use of many elements of GDELT in concert with advanced modeling techniques to demonstrate the unique lens that GDELT provides onto the global world.