Television Emotions Explorer
As part of our efforts to leverage the Internet Archive's Television News Archive to better understand how television news captures and portrays domestic and global events and narratives, we've created this tool that attempts to assess at a macro level the emotional undercurrents of American television news each day. The full closed captioning streams of all news shows aired on each monitored station each day are run through the entire English language GDELT GCAM emotion pipeline, totaling almost 2,500 discrete emotions. Refer to the specific documentation of any given package for more detail about how each dimension is defined and calculated. All emotional scores reported here were calculated completely automatically using the specified dictionary operating in "bag of words" mode. All output is therefore completely algorithmic and automated and does not reflect any editorial statements about the respective networks. The Y axis scale and range varies by dimension, please see the documentation for each specific dimension for further details. Data is based on scanning the closed captioning records of each broadcast, which are subject to a degree of error. NOTE that aggregations of stations may have increased variability the further back you look due to stations being added to some aggregations over time and increasing the total volume of material being analyzed. Those wishing to export the data below in CSV format for further analysis, you can append "&output=csv" to the URL of this page to export the raw timeline in CSV format.
Email kalev.leetaru5@gmail.com with any questions. Permission is granted for any and all use of these graphs in media reports, please cite "Analysis by the GDELT Project using data from the Internet Archive Television News Archive" and report the specific emotion appearing in the Emotion dropdown, such as "Emotion: Anxiety by the Regressive Imagery Dictionary."
Use the options below to select which network(s), time period and emotion to display.