Visualizing the Emotions of American Television News

You are here

Type: 
Blog
Author: 
GDELT project
Year: 
2014
Org.: 
The GDELT Project
Language: 
English
Difficulty: 
Not Applicable
Tags: 
Kennisbank, Kennisbank
Topics: 
 

The latest GDELT Project release is a new dataset of all 540,000 hours of English-language American television broadcasts held by the Internet Archive's Television News Archive  processed to extract the complete list of people, organizations, disambiguated locations, and more than 2,238 emotions and themes from each broadcast. The complete dataset (only the extracted metadata, not the broadcasts themselves) is available for download, along with an interactive viewer timeline that allows you to visualize a particular emotion or theme over the last four years of American television news.  The user can try Anxiety to see the impact of the US Government shutdown in October 2013 or Holidays to see the cyclic discussion of the holiday season each year. The timeline displays the density of the selected emotion/theme across all monitored television broadcasts on all networks monitored by the Internet Archive by day, representing the percentage of words in those broadcasts connoting this emotion/theme. The blue line shows the raw density scores by day, while the red line displays a 7-day rolling average to smooth the data and make macro-level patterns more apparent.An additional barchart shows the breakdown by television network of where the selected emotion appears in the greatest density.

Interesting example of data mining in television news presented online in a way that can support research.