Q&A: How we used large language models to identify guests on popular podcasts
We asked researchers how they used the newest generation of large language models to analyze roughly 24,000 podcast episodes.
Numbers, Facts and Trends Shaping Your World
We asked researchers how they used the newest generation of large language models to analyze roughly 24,000 podcast episodes.
Pew Research Center conducted a study to compare the accuracy of six online surveys of U.S. adults – three from probability-based panels and three from opt-in sources. On average, the absolute error on opt-in samples was about twice that of probability-based panels.
Modern survey tools offer several ways to survey small populations, and in this explainer, we discuss the strengths and weaknesses of prominent approaches.
A new study found that 61% of national pollsters used different methods in 2022 than in 2016. And last year, 17% of pollsters used multiple methods to sample or interview people – up from 2% in 2016.
National polls like the Center’s come within a few percentage points, on average, of benchmarks from high response rate federal surveys.
Pew Research Center makes most of its datasets available for download once reporting has been completed for a given study. Here’s how to find and access our data.
If you’ve wondered what opinion polls are for, how they are done or how to tell a good one from a bad one, sign up for our email mini-course.
Public polling estimates on COVID-19 vaccination have been within about 2.8 points, on average, of the CDC’s calculated rate.
Since the initial disruptions of field operations due to COVID-19, we have been able to conduct 33 surveys in 17 countries and territories.
One method to improve survey representation of the non-internet and less literate population is to allow people to take surveys offline. In March, we fielded a study to test the feasibility and effect of collecting data through respondent-initiated interactive voice response; here’s what we found.