Over the last twenty years, the rise of email newsletters and podcasts has enabled an industry of political pundits to expound on what’s right and wrong, and to tell us the likely outcome of this or that political action. I wanted to test out the efficacy of pundits, so with the assistance of AI, back in April I built a system to pull in more than 80 left, center, and right-wing political newsletters and podcasts, and launched it as newsletterzeitgeist.site. Every day it runs a summary of the day’s punditry and keeps transcripts of everything collected. Using that database, I set AI on an analysis task of more than 16 million words between September 1 and November 14. I asked two questions, with the conclusions as follows:
When the language arrived: sentences per 10,000 words that predict a blue wave or a broad Democratic victory, by week. Weeks start on the date shown; the last point is election day alone.
For the most part, Democrats were slightly more optimistic about a broad Democratic victory over time. But around October 20, anticipation of a wave built among all groups built. This coincides with the October 19 launch of Vivek Ramaswamy’s “mother” ad (see “Did Pundits Notice 2026 Election Turning Points”). But then, on October 27, Nate Silver posted a story suggesting the final NYT/Siena poll might be right, predicting a +11 Democratic wave. Even that size of a win was not fully accepted by all pundits - and nobody saw the magnitude of a +14 Democratic victory as not even in the realm of possibility.
Full details and analysis here.
Vocabulary change by day: how different the two-word terms used in the five days starting that day were from the five days before. Higher means a sharper break. The numbered lines mark the seven campaign dates tested.
Most of the identified dates did not show a significant shift in tone - except for the launch of Ramaswamy’s ad among left-wing pundits and the Haley Stevens endorsement among centrists. When viewing the data as a continuum, it is hard to see that pundits had any kind of consistent foresight, and that when viewing events that have occurred, there seems to be almost no connection between “major” events and how pundits discussed the likely election outcome.
Full details and analysis here.
Additional information: Political Pundit 2026 Campaign Word Clouds