Correlation Analysis Using Global Dataset of Events, Location and Tone

The GDELT is a real time database of global human society for open research which monitors the world's broadcast, print, and web news, creating a free open platform for computing on the entire world. GDELT contains three data tables: Event, Mentions and GKG while most researches are based only on the Event table. Using big data techniques like HDFS, Hive and Spark, we design and propose a hash-based method to efficiently correlate these three data tables in order to provide further detail insights about events contained in the whole GDELT dataset. In addition, case studies such as heat map and bubble chart are visualized with event data in South Korean extracted from the correlated GDELT dataset.