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.
Key Takeaways:
1 | Joe Biden | 250,201 |
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
1 | Elizabeth Warren | 35,928 |
2 | Cory Booker | 22,299 |
3 | Beto O’Rourke | 19,461 |
4 | Julián Castro | 16,121 |
5 | Amy Klobuchar | 14,691 |
6 | Bill de Blasio | 14,522 |
7 | Jay Inslee | 10,965 |
8 | Tulsi Gabbard | 9,527 |
9 | John Delaney | 9,398 |
10 | Tim Ryan | 8,729 |
1 | Joe Biden | 52,891 |
2 | Bernie Sanders | 36,129 |
3 | Kamala Harris | 30,062 |
4 | Pete Buttigieg | 16,748 |
5 | Eric Swalwell | 9,073 |
6 | Kirsten Gillibrand | 8,040 |
7 | Marianne Williamson | 7,726 |
8 | John Hickenlooper | 6,517 |
9 | Andrew Yang | 6,272 |
10 | Michael Bennet | 5,696 |
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.