EVENT Geographic Network Visualizer

EVENT Geographic Network Visualizer

Dataset: GDELT Event Database

Description:Creates a geographic network of the cities and landmarks connected through events and produces a set of images and georeferenced network files.

Components: PERL, GraphViz, Google BigQuery

Acknowledgements: Makes use of GraphViz to create the preview images and Google BigQuery.

Examples: Geographic Networks: Contextualizing Relationships in Space

The EVENT Geographic Network Visualizer allows you to rapidly construct georeferenced networks through the GDELT Event Database to understand how the cities of the world are connected through events matching your search, and creates a set of visualizations and output files. A list of all events matching your search criteria are compiled and a link formed between the geographic locations of Actor 1 and Actor 2 of each event. The resulting georeferenced network captures how the locations of the world are connected through different kinds of events. Two preview images are created, one with white edges drawn on a black background to make the overall structure of the network immediately clear, while the other colors each location and edge by its average Goldstein Score from bright red (high conflict) to bright green (high cooperation), offering the ability to see how certain locations are paired in more conflictive or more cooperative light. A Google Earth .KML file allows you to load the network into Google Earth, including all of the connections among locations. A special Gephi .GEXF file is generated that encodes the latitude and longitude information of the network and the coloring of each edge, suitable for layout through Gephi's Geo layout algorithm. Finally, two GraphViz .DOT files are created that can be loaded into a number of different network analysis packages or rendered using GraphViz to produce the two preview images.

No programming or technical skills are required to use this visualization - you simply specify a set of criteria for the event type and actors involved, along with an optional date range, and the system will automatically search the entire GDELT Event Database for all matching events and compile the final geographic network. Your results will be emailed to you when complete, usually within 10 minutes, depending on server load and the time it takes to perform the necessary calculations. Selecting "Nigeria" as the "Event Location", "Material Conflict" as the "Event Quad Class", and "Civilian" as the "Recipient/Victim (Actor2) Type" will generate a geographic network of attacks and other conflict against civilians in Nigeria.

Your Email Address

Creating these results can take several minutes depending on server demand - please provide the email address that the results should be sent to.

Email Address

Date Range

Limit the time period of analysis. The earliest allowable date for event data is currently January 1, 1979 and the latest date allowed is the current day.

Start Date
End Date
 

Search Criteria - Actors

Select the specific actors involved in the event. The CAMEO taxonomy used by GDELT codifies an "event" as an action performed by one entity (Actor1) onto another (Actor2). GDELT codifies an array of 58 fields of information about each event. Using the form below you can restrict your search to just those events initiated by a specific country and/or type against another country and/or type. For example, to select all attacks on civilians in Nigeria, you would specify "Civilians" using the "Actor2 Type" dropdown below, "Nigeria" using the "Event Location" dropdown below, and then violence-related event types using the next section. To select all protests in Nigeria, you would leave the Actor section below blank, and select protest-related event types from the following section and "Nigeria" as the "Event Location."

Initiator (Actor1) Country:

Initiator (Actor1) Type:

Recipient/Victim (Actor2) Country:

Recipient/Victim (Actor2) Type:

Search Criteria - Event

Select the specific type and/or location of events you are interested in. The full CAMEO taxonomy defines over 300 specific categories of events, but to simplify things, the search interface below lets you search only for the 20 root categories under which those other event types fall, or you can select by "Quad Class", which groups the 20 root categories into 4 "super categories".

Event Code:
     OR     
Event Quad Class:

Event Location:

Location Weighting

How should the "weight" of each location be calculated?

  • Number Events Each location is weighted by the total number of unique events found at that location, irrespective of how much news coverage each event received. This is useful to look strictly at the overall distribution of events, where all events are considered equal. Using this weighting, an event that is covered by 10,000 different news reports across the world will count the same as one that received just a single news report. This yields the best overall picture of where things are happening, but not necessarily where the "most important" ones are happening.
  • Number Articles Each location is weighted by the total number of news articles covering events found at that location. Using this weighting, an event that is covered by 10,000 different news reports across the world will count as 10,000 times more important as one that received just a single news report. This option uses the volume of media coverage of each event as a proxy for its perceived "importance" and thus offers the best overall picture of where the "most important" events are taking place (as measured by media coverage).

Cutoff Thresholds

If your network ends up being too large or too small, you may decide to adjust the cutoff thresholds below. Node Cutoff sets how many events/articles a location must appear in before it is included in the graph, while Edge Cutoff sets how many events/articles must connect a pair of locations before they are connected in the network. The counts measured by these cutoffs are affected by your selection in the Edge Weighting section above.

Node Cutoff
Edge Cutoff
 

Outputs

The following output files will be generated:

  • Google Earth .KML File This outputs a .KML file that can be opened in Google Earth that color-codes each city and connection among them from bright red (strongly conflictive) to bright green (strongly cooperative). These files are usually too large to be previewed in Google Maps, but the free edition of Google Earth (https://www.google.com/earth/) can display them easily. They can also be loaded into many GIS applications.
  • Geographic Gephi File This outputs a Gephi .GEXF file that color-codes each city and connection among them from bright red (strongly conflictive) to bright green (strongly cooperative). The file includes special latitude and longitude attributes on each node and the new GEXF version 1.2 edge coloring to allow network links to be colored according to Goldstein Scale. If you install Gephi's "Geo" layout algorithm you can render this in map format directly in Gephi.
  • Goldstein Scale Network .DOT Graphviz File Generates a .DOT file in the Graphviz file format that color-codes each city and connection among them from bright red (strongly conflictive) to bright green (strongly cooperative). This file can be directly imported into GraphViz's "neato" utility for rendering or into any package that supports the .DOT format for further analysis.
  • Goldstein Scale Network Preview Image Generates a .PNG preview image of the Goldstein Scale Network, rendered using GraphViz. Nodes and edges are made semi-transparent so that only the strongest connections are visible.
  • Intensity Network .DOT Graphviz File Generates a .DOT file in the Graphviz file format that records each city and connection among them. Nodes and edges are NOT color-coded, they are designed to render out as white lines that can be overlaid onto a dark map. This map makes macro-level spatial patterns easiesr to spot than the Goldstein Scale map above. This file can be directly imported into GraphViz's "neato" utility for rendering or into any package that supports the .DOT format for further analysis.
  • Intensity Network Preview Image Generates a .PNG preview image of the Intensity Network, rendered using GraphViz. Nodes and edges are made semi-transparent so that only the strongest connections are visible. Black background makes it easier to spot macro-level patterns.