Can AI Stand In for Human Survey-Takers? Not Really
Synthetic surveys using digital twins do a poor job estimating the public mood and are especially error-prone for some subgroups, including Republicans and Black adults.
Numbers, Facts and Trends Shaping Your World
Synthetic surveys using digital twins do a poor job estimating the public mood and are especially error-prone for some subgroups, including Republicans and Black adults.
All
Publications
While the possibility of falsified data is an important consideration in survey research, a new tool to detect it fails to perform as advertised.
The claim by Kuriakose and Robbins (2015) that there is widespread falsification in international surveys is clearly concerning. However, an extensive investigation conducted by Pew Research Center finds the claim is not well supported.
High-profile polling failures in recent elections have drawn attention to the challenges in using surveys to predict outcomes. Our study examines various methods of determining who is a likely voter.
While survey research in the United States is a year-round undertaking, the public’s focus on polling is never more intense than during the run-up to a presidential election.
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.
Members of the American Trends Panel can now take our surveys online or over the phone with an interviewer.
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.