In an update to our initial tracking of the US Democratic Party presidential primaries, here we track and analyse media coverage for the major democratic candidates in the month of June.
Using Artificial Intelligence, we have tracked every time the candidates are referred to in the media throughout June, on the days of the first democratic debates, and the days following.
Total Media Coverage (all candidates): 501,663
- The candidates were mentioned a total of 1,204,623 times in over half a million articles across June.
- Unsurprisingly the biggest drivers for coverage this month were the debates on June 26 – 27.
- The second debate proved more popular than the first, with over 67,000 news pieces about it.
- By comparison, the first debate was covered in just under 52,000 pieces.
- Harris gained the greatest increase to coverage from the debates.
- Whilst she placed fourth for the month as a whole, since has only been beaten, in terms of coverage, by Biden.
- She received almost half of her month’s coverage (42,000 articles) in the last three days of the month.
- Some 30,000 of these articles mentioned her attacks against Biden for his previous positions on busing.
|2||Sen. Bernie Sanders||165,180|
|3||Sen. Elizabeth Warren||137,657|
|4||Sen. Kamala Harris||90,669|
|5 (+1)||Sen. Cory Booker||74,253|
|6 (-1)||Pete Buttigieg||66,061|
|7 (+1)||Beto O’Rourke||57,457|
|8 (-1)||Bill de Blasio||49,048|
|9||Sen. Amy Klobuchar||38,672|
|10 (+4)||Julián Castro||35,399|
|11 (-1)||Sen. Kirsten Gillibrand||31,705|
nb. All times are BST
|6||Bill de Blasio||14,522|
About the Index
Our index uses Artificial Intelligence (AI) so that we can track candidates as trained ‘entities’.
Traditionally, tracking has relied on imprecise keyword searches or clunky Boolean strings. This has issues. For example, searching for ‘John Delaney’ as a key word would surface content not only about Rep. John Delaney, but also John Delaney, the Chief Executive Officer of the Football Association of Ireland. Previous coverage analysis, by other organisations, has relied on “a name appearing in a story” to count as a mention. This leads to inaccurate and incomplete research.
An ‘entity’ can be any organisation, individual, location, or event. In this case we have trained our AI to recognise any time the Democratic candidates are mentioned. It understands context, synonyms, antonyms, and can disambiguate similar or identical keywords. This allows us to capture a much more complete picture of the candidates. For example, our AI registers if Sen. Bernie Sanders has been referred to, regardless of how he is referred to – be it “Sanders, Sen. Sanders, ‘Crazy Bernie’, United States Senator from Vermont, etc.”
For more information on entities please see here.
Using entities allows us to build the most complete image of a candidate’s coverage in the world.
Signal AI is an apolitical, nonpartisan organisation. We research the primaries because they interest us, not in order to impact them. We are not responsible for how people use our work.
Image Source: Cropped use of U.S. Senator Kamala Harris speaking with attendees at the 2019 National Forum on Wages and Working People hosted by the Center for the American Progress Action Fund and the SEIU at the Enclave in Las Vegas, Nevada (27 April 2019), by Gage Skidmore via flickr.com.