** The following commentary was published a month ago following the 3rd Democratic debate and data mentioned below is from that period. It highlights the winners and losers as based on a variety of metrics, including ZettaCap’s SMI. It follows the same analysis format that was used for the 1st and 2nd round of debates.
As had been forecasted prior to the 3rd debate, Andrew Yang performed extremely well. Further, due to his impressive SMI both before and during the debate, we stated that he could become the ‘it’ candidate at least for a time. For a short period it seemed as though this was the case as his social media metrics as well as his news media mentions improved post-debate. This trend ended due to the emergence of the impeachment proceedings which has thrown the 2020 nomination process for a loop.
To-date, the Democratic race has been characterized by brief surges in SMI by various candidates which have proven fleeting. Yang’s 3rd debate surge could be yet another.
This pattern implies that a true front-runner has yet to emerge within the declared Democratic candidates. As previously reported, we believe the door is still open for a new candidate to declare given consistently attractive SMIs of undeclared Democrats.
Tonight is the 4th Democratic debate. (10/15/2019)
=============================
Summary
Andrew Yang was by far the winner of the 3rd Democratic debate. Social Media Influence (SMI), our main election forecasting tool, put him in 1st place, two on-line surveys also had Yang winning, and Google Trends during the debate put him in a solid 2nd place. In short, Yang took the night.
Bernie Sanders also registered a solid performance across a variety of alternative metrics. Beto O’Rourke outperformed, especially when using SMI and search trends, proving his relevance in the race after a period of decline.
Elizabeth Warren and Kamala Harris underperformed. Going into the 3rd debate, many mainstream pundits expected Warren to dominate the debate given her rising status in polls and betting markets. Her debate performance, however, was mediocre at best, placing around the middle of the pack, depending on the metric.
Joe Biden, still leading in national polls, posted a moderate performance. In an unusual twist, his metrics benefited from protesters who interrupted one of his replies which resulted in searches for the topic and social media users trying to figure out what had happened.
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 ten candidates 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. | |
| Yang | 1 | 1 | 1 | 2 | 3 | 1.6 |
| Buttigieg | 2 | 4 | 5 | 8 | 7 | 5.2 |
| O’Rourke | 3 | 6 | 7 | 7 | 2 | 5.0 |
| Sanders | 4 | 2 | 2 | 4 | 4 | 3.2 |
| Biden | 5 | 3 | 3 | 1 | 1 | 2.6 |
| Harris | 6 | 9 | 9 | 3 | 6 | 6.6 |
| Booker | 7 | 8 | 8 | 9 | 9 | 8.2 |
| Warren | 8 | 5 | 4 | 5 | 5 | 5.4 |
| Castro | 9 | 10 | 10 | 6 | 8 | 8.6 |
| Klobuchar | 10 | 7 | 6 | 10 | 10 | 8.6 |
Source: ZettaCap, Heavy, Washington Examiner, Google Trends
There seems to be a general agreement that Yang did well in the debate, independent of the source of data. Social media, on-line searches and on-line surveys all point to Yang as having had a standout performance.
Bernie Sanders logged an adequate performance in the debate, more or less in-line with his traditional metrics. National polls normally have Sanders in either second or third place whereas betting markets have him in third. SMI placed him in fourth during the debate, while an average of the various metrics in Table 1 put him in third.
Beto O’Rourke’s debate figures generally beat expectations based on traditional metrics. National poll averages place him tied for sixth place whereas betting markets have him in tenth place. Figures from Table 1 have him placing fourth using the average of the metrics and third using just SMI. This debate has offered O’Rourke an opportunity to climb back into top-tier status.
In contrast, Booker, Castro, and Klobuchar all performed poorly across the various metrics. These three candidates will need to reset their respective campaigns if they wish to remain relevant.
Other candidates seem to have produced a mixed bag in that they scored well on some metrics but poorly on others.
For instance, Elizabeth Warren came in eighth in SMI and fourth or fifth on other metrics. We should highlight that Warren is currently seen by the consensus as the likely nominee. She has a fairly large 11 percentage point lead in betting markets (predictit.org) while coming in second using an average of national polls (realclearpolitics.com). Her debate metrics do not support her attractive traditional metrics.
We should also take a closer look at Joe Biden’s performance. His SMI and on-line surveys put him as a mediocre to strong candidate, finishing fifth and third respectively. However, he really stood out in Google search both during the debate as well as after, which improves the interpretation of his overall performance. But, were sharp improvements in search trends a reflection of his performance or some other factor?
Biden’s top search ranking seems to come from the fact that protesters interrupted one of his debate replies. Consequently, ‘related queries’ for Biden included the protester incident.
It is questionable if such weight should be given to a top ranking if the searches were inspired by something like a debate protest and not a more positive factor. This is a reasonable example of how alternative data can be misinterpreted. It also, frankly, shows that no indicator or model is free from bias or misinterpretation.
Regardless of Google search results, Biden did well enough in terms of SMI and on-line surveys to keep his campaign moving along. Given the perception that his electability is strong, Biden’s current debate performance was sufficient to keep him as one of the top-tier candidates.
Is Yang the New ‘It’ Candidate?
The week prior to the 3rd debate, we openly speculated this very question. Given his unusually strong and surging SMI, we forecasted that “he will soon become the new ‘it’ candidate”.
Now, post-debate, we clearly see that our observations have hit the mainstream. Social media greeted his debate performance much more positively than any other candidate. On-line surveys, both conservative and liberal based, had him winning (as did other on-line surveys that we did not quote). And, Google search trends had him as one of the top searches among candidates both during the debate and the following day.
These rather broad based data help to highlight his implied on-line influence, as well as the support and interest from the electorate.
Other candidates such as Gabbard and Williamson performed similarly well using alternative metrics during previous debates and they were not able to translate such performance in a broader post-debate trend.
What could make Yang different from Gabbard and Williamson is that his SMI was surging into the debate and not simply because of the debate. The combination of a broad based positive debate performance and surging pre-debate SMI greatly increases the chances of Yang emerging as the ‘it’ candidate.
This does not mean that he is forecast to win the nomination, just that we expect him to gain an unusual amount of attention over the coming month as he gains more of the spotlight.