Our 2020 Democratic Primaries Index has been updated for June and July.
At Signal AI we’ve been tracking media coverage of the US Democratic Party presidential primaries – analysing media pieces from the largest set of sources in the world, in over 80 languages, crossing all sorts of media (print, online, and broadcast).
Using Artificial Intelligence, we’ve been able to track every time any candidate is referred to, even if not by name.
Between January 1 and May 31 total we’ve clocked 2,949,748 references to the major Democratic candidates, in 1,716,201 different news items. President Donald Trump, by comparison, has appeared in 8,184,437 pieces in the same period.
Over half (57.7%) of this coverage has been on four of the candidates: Sen. Bernie Sanders, Joe Biden, Sen. Elizabeth Warren, and Sen. Kamala Harris.
1 | Sen. Bernie Sanders | 528,190 | 13 | Rep. Tulsi Gabbard | 50,371 |
2 | Joe Biden | 525,456 | 14 | John Hickenlooper | 41,978 |
3 | Sen. Elizabeth Warren | 383,490 | 15 | Rep. Eric Swalwell | 32,322 |
4 | Sen. Kamala Harris | 264,632 | 16 | John Delaney | 28,085 |
5 | Sen.Cory Booker | 182,146 | 17 | Rep. Tim Ryan | 26,224 |
6 | Beto O’Rourke | 164,670 | 18 | Sen. Michael Bennet | 24,401 |
7 | Sen. Kirsten Gillibrand | 129,850 | 19 | Gov. Steve Bullock | 23,883 |
8 | Sen. Amy Klobuchar | 125,768 | 20 | Andrew Yang | 21,763 |
9 | Mayor Pete Buttigieg | 120,941 | 21 | Rep. Seth Moulton | 18,489 |
10 | Mayor Bill de Blasio | 102,305 | 22 | Marianne Williamson | 10,036 |
11 | Gov. Jay Inslee | 76,915 | 23 | Mayor Wayne Messam | 4,321 |
12 | Julián Castro | 60,961 | 24 | Mike Gravel | 2,551 |
From June, we will be producing analysis of the Democratic presidential race on a regular basis. This analysis will look at things such as, sentiment towards the candidates, coverage in key states, and topic specific coverage.
1 | Sen. Elizabeth Warren | 72,760 |
2 | Sen. Bernie Sanders | 62,529 |
3 | Sen. Kamala Harris | 55,468 |
4 | Joe Biden | 35,013 |
5 | Sen. Kirsten Gillibrand | 27,275 |
6 | Julian Castro | 19,589 |
7 | Sen. Cory Booker | 17,620 |
8 | Rep. Tulsi Gabbard | 16,967 |
9 | Bill de Blasio | 15,833 |
10 | Beto O’Rourke | 14,181 |
Total Coverage (all candidates): 392,735
Key Takeaways:
1 (+1) | Sen. Bernie Sanders | 102,072 |
2 (-1) | Sen. Elizabeth Warren | 87,679 |
3 (+0) | Sen. Kamala Harris | 65,618 |
4 (+3) | Sen. Cory Booker | 58,121 |
5 (-1) | Joe Biden | 39,503 |
6 (+4) | Sen. Amy Klobuchar | 37,521 |
7 (-2) | Sen. Kirsten Gillibrand | 32,835 |
8 (+2) | Beto O’Rourke | 24,821 |
9 (+0) | Bill de Blasio | 23,498 |
10 (-2) | Rep. Tulsi Gabbard | 11,770 |
Total Coverage (all candidates): 524,294
Key Takeaways:
1 (+0) | Sen. Bernie Sanders | 114,354 |
2 (+4) | Joe Biden | 86,798 |
3 (-1) | Sen. Elizabeth Warren | 72,659 |
4 (+4) | Beto O’Rourke | 63,706 |
5 (-2) | Sen. Kamala Harris | 44,803 |
6 (-2) | Sen. Cory Booker | 35,835 |
7 (-1) | Sen. Amy Klobuchar | 28,557 |
8 (-1) | Sen. Kirsten Gillibrand | 28,133 |
9 (+2) | Gov. Jay Inslee | 21,534 |
10 (+6) | John Hickenlooper | 19,139 |
11 (-2) | Bill de Blasio | 15,442 |
14 (-4) | Rep. Tulsi Gabbard | 8,241 |
Total Coverage (all candidates): 594,814
Key takeaways:
1 (+1) | Joe Biden | 222,381 |
2 (-1) | Sen. Bernie Sanders | 152,935 |
3 (+0) | Sen. Elizabeth Warren | 81,153 |
4 (+7) | Pete Buttigieg | 54,390 |
5 (+0) | Sen. Kamala Harris | 50,007 |
6 (-2) | Beto O’Rourke | 37,240 |
7 (-1) | Sen. Cory Booker | 35,361 |
8 (-1) | Sen. Amy Klobuchar | 24,447 |
9 (-1) | Sen. Kirsten Gillibrand | 20,145 |
10 (-1) | Gov. Jay Inslee | 17,031 |
17 (-7) | John Hickenlooper | 7,988 |
Total Coverage (all candidates): 799,599
Key Takeaways:
Total Coverage (all candidates): 628,306
Key Takeaways:
You can find our June update here.
Our index uses Artificial Intelligence 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 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 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.