Summary
The big winner of the 7th Democratic debate was Bernie Sanders. Social Media Influence (SMI), our main election forecasting tool, put him at the top, as did the on-line post-debate surveys of who won the debate, as highlighted in Table 1. Furthermore, Sanders came out on top according to Google Trends, using the data from the day following the debate which oftentimes is a better predictor of interest than during the debate. Across various metrics, Sanders won the night.
Amy Klobuchar was the largest positive surprise, as she was in the 6th debate as well. Her second place SMI finish matched her performance in the 6th debate. In terms of the average of the metrics we highlight in Table 1, she came in 2nd behind Sanders.
Biden and Warren continue their pattern of poor debate performances. SMI placed them at the bottom of the field and their broader debate metrics in general look weak. We have noted similar observations for these two candidates after previous debates. Their under-performance according to our metrics has been in direct contrast to polls, betting markets, and pundits that have placed them at or near the top of the field for 2019 and 2020.
As noted in recent posts, we expected Sanders to perform well in the 7th debate given his recent SMI momentum and strength. With an impressive debate performance verified, he looks to have a considerable advantage going into Iowa voting.
There is still considerable space to maneuver in this race. Sanders is the new front-runner according to SMI but much of his improvement appears to be due to AOC’s endorsement (as referenced here and here) which leaves open to question his staying power if/when other high-profile Democrats endorse other candidates or if AOC does not continue campaigning for him. Also, we continue to see the Democratic field as fragmented and relatively weak as compared to other elections. The bottom line is that there still appears to be room for late entrants and/or political maneuvering.
Even though Sanders has the best position going into Iowa (having definitively won the last debate prior to voting, having taken the SMI lead, and showing the strongest momentum), we still see this nomination as up in the air. Sanders has the advantage at present but the race is far from over.
The Data
There are three different types of data in Table 1 (below).
SMI uses social media data to measure on-line influence. The next two entries, Heavy and Washington Examiner, are on-line surveys asking who won the debate. We specifically chose a left-leaning (Heavy) and right-leaning (Washington Examiner) survey sources to see if there was any difference. The last two refer to Google Search popularity during the debate and during a peak period from the next day to see how trends might have shifted post-debate when people search to find out more about a candidate.
It is important to state that SMI’s rankings are completely independent of the other forms of analysis — and that SMI provides similar yet unique insights.
Additionally, we should highlight that SMI made early and correct forecasts for the 2016 US Election, 2017 French Election, and 2018 Brazil Election – all considered extremely difficult elections to correctly forecast.
Comparative Rankings
The following table lays out the ranked finish of each of the seven candidates participating in the debate according to a variety of methods.
Table 1: Ranking by Candidate’s Debate Performance by a Variety of Methods
| SMI | Heavy.com (Survey) | WashingtonExaminer.com (Survey) | Google Search, during debate |
Google Search, next day
|
Avg. | |
| Bernie Sanders | 1 | 1 | 1 | 3 | 1 | 1.4 |
| Amy Klobuchar | 2 | 5 | 3 | 1 | 3 | 2.8 |
| Tom Steyer | 3 | 6 | 6 | 2 | 6 | 4.6 |
| Pete Buttigieg | 4 | 2 | 2 | 6 | 5 | 3.8 |
| Joe Biden | 5 | 4 | 5 | 5 | 4 | 4.6 |
| Elizabeth Warren | 6 | 3 | 4 | 4 | 2 | 3.8 |
Source: ZettaCap, Heavy.com, WashingtonExaminer.com, Google Trends
Focusing on SMI data, Bernie Sanders was the winner. He has now finished in the top 3 during the last 4 debates, making him one of the most consistent top performers. Especially in comparison to other candidates who also poll well (such as Biden and Warren), Sanders’ SMI and debate performances are more consistently near the top.
In addition to an SMI victory, he also won both on-line surveys. Interestingly, we chose one left-leaning and one right-leaning site as sources of the surveys, and Sanders won both. In the Drudge Report’s on-line survey, which does not appear in Table 1, Sanders came in a close second behind Klobuchar.
Google search trends also showed Sanders near the top. According to Google search trends taken during the debate, he came in 3rd, however it appears that he was pushed down by searches related to non-political topics (Klobuchar’s eyebrows and Steyer’s hand drawings). Sanders moved to 1st place the day following the debate as such non-political searches became less prevalent.
Amy Klobuchar posted an extremely impressive performance considering she is not seen as a top-tier candidate by the consensus based on polls (7th place) and betting markets (8th place). SMI and the average of the metrics in Table 1 have Klobuchar in 2nd place in the last debate prior to Iowa voting. For most, this is unexpected. Given her positive performances in the 6th and 7th debates, she could still impact the race though becoming a dark horse candidate at this late stage is unlikely.
Pete Buttigieg had a reasonably good debate performance. It was good enough, especially the 2nd place finishes in the on-line surveys, to keep him near the top. But not good enough to standout, given his disappointing SMI and search trend results.
The real disappointments came from Biden (leading in both polls and betting markets) and Warren (3rd in both polls and betting markets). The fact that these two candidates consistently post mediocre to poor debate performances according to alternative metrics should be extremely worrying for Democrats. It depicts a voter base, very close to the start of voting, that does not appear enthusiastic or supportive of these candidates.
Andrew Yang’s ‘Performance’
Yang did not qualify for the 7th debate but continues as a candidate. Because he did not participate, we cannot include him in Table 1. However, we can view his SMI and Google search trends and compare them to those of the candidates who did compete in the debate.
Yang’s SMI during the debate is only slightly lower than that of Sanders, the winner of the night.
Yang’s next day Google search trend would put him in 3rd place.
And, he was not even on the debate stage.
Normally, candidates not participating in a debate fall off the radar and are completely overlooked during and soon after the debate. This should be expected as so much activity on social media and in search is focused on the debate and the candidates on the stage. In other words, Yang is not supposed to perform so well if not on the debate stage.
As covered previously, Yang won debates 1 -6 according to on-line surveys and debates 3 – 6 according to SMI. Such figures show that his followers are extremely enthusiastic and that his message has gained traction. This trend appears to have continued even though not having qualified for the last debate.
We speculated that the enthusiasm of Yang’s supporters could create an imagined second fault line in the Democratic Party, with the first being between the Sanders/Warren left and Biden/Klobuchar center. This second fault line would be between Yang (and his Universal Basic Income platform) and the rest of the Party.
Yang’s strength on the night, even though he did not make the stage, supports this concept.
Vs. Our Expectations
The debate went more or less along the lines we were expecting.
Debate 7 more or less played along to the script — or, at least our script.