{"id":574140,"date":"2026-09-30T13:55:20","date_gmt":"2026-09-30T17:55:20","guid":{"rendered":"https:\/\/alpha.pewresearch.org\/pewresearch-org\/?p=574140"},"modified":"2026-09-30T13:55:20","modified_gmt":"2026-09-30T17:55:20","slug":"how-well-synthetic-polls-capture-the-diversity-of-public-opinion","status":"publish","type":"post","link":"https:\/\/alpha.pewresearch.org\/pewresearch-org\/data-labs\/2026\/09\/30\/how-well-synthetic-polls-capture-the-diversity-of-public-opinion\/","title":{"rendered":"How well synthetic polls capture the diversity of public opinion"},"content":{"rendered":"\n
About this research<\/summary>\n

This Pew Research Center report examines whether AI-generated survey data can accurately duplicate the results of high-quality public opinion polls.<\/p>\n\n\n\n

We conducted this methodological experiment to better understand an emerging method in survey research. The Center believes that speaking to the public is essential to measuring public opinion and has no current or future plans to use AI models to generate survey results. Read more about our AI policy<\/a>.<\/p>\n\n\n\n

For this study, we had an AI model take on the role of real respondents from our American Trends Panel<\/a> (ATP) and answer the same surveys administered to human panelists. These surveys included many different question formats and asked about a wide range of topics, attitudes and behaviors.<\/p>\n\n\n\n

Why did we do this?<\/h4>\n\n\n\n

The Center regularly studies and evaluates advances and trends in polling research<\/a>. As AI-based polling becomes more widely used in the industry<\/a>, we wanted to understand the data these \u201csynthetic samples\u201d produce and how it compares with high-quality surveys of real humans on topics of broad public interest. That question is the focus of this study; it does not address other uses of AI models in polling.<\/p>\n\n\n\n

How did we do this?<\/h4>\n\n\n\n

We used a \u201cdigital twins\u201d approach for this study, asking an AI model to adopt the personas of real humans who are members of the ATP. We gave the model a wide range of information about each panelist<\/a>, including their self-reported demographic information and their responses to questions on our 2025 political typology survey<\/a>. We then showed the model questions from three different ATP surveys conducted in the first half of 2026 and asked it to respond to those same questions as the assigned persona. The model was given each question on the survey in order from start to finish, with exactly the same instructions and survey programming that the real humans who took it received.<\/p>\n\n\n\n

To make a direct comparison between our AI and human polls, we only replicated surveys for the ATP panelists from each wave who had also completed the political typology survey. As a result, figures for U.S. adults in this report may differ slightly from those previously published by the Center.<\/p>\n\n\n\n

We tested multiple models, but all synthetic results unless noted otherwise come from Anthropic\u2019s Claude Opus 4.6. At the time we conducted this study, Opus 4.6 was the most recent Anthropic model available for commercial use and had the best performance of several we evaluated.<\/p>\n\n\n\n

Here are the survey questions from Wave 185<\/a>, Wave 190<\/a> and Wave 192<\/a> used for this analysis, the detailed responses<\/a> from the ATP and AI surveys, and the methodologies<\/a> for the original ATP survey waves and our AI surveys.<\/p>\n<\/details>\n\n\n\n

Traditional public opinion polls are often marked by the diverse views they show within a population. While the broad contours of public sentiment are often clear, there are very few opinions that are universally held. By the same token, most of the answer choices on a typical survey question \u2013 from the extreme to the middle-of-the-road \u2013 are selected by at least a modest number of respondents.<\/p>\n\n\n\n

In our analysis of synthetic polling, AI respondents tended to eliminate a great deal of this diversity. On some questions, the model assumed most Americans\u2019 views are far more extreme than they actually are. On others, it assigned the vast majority of respondents to the middle category in a set of choices. And across questions of all types, our AI survey-takers collectively avoided certain answer choices in ways that have no parallel among their human counterparts.<\/p>\n\n\n\n

Even if the model\u2019s results point in the same general direction as true public opinion, they ultimately paint a picture that is less diverse and more one-note than what we see in actual polls of human respondents.<\/p>\n\n\n\n

This analysis is part of a larger evaluation of AI-generated synthetic samples in public opinion research. Read<\/em> a summary of the main findings<\/a><\/em> and refer to the<\/em> methodology<\/a><\/em> for more details on how we conducted our synthetic poll and compared it with real survey results.<\/em><\/p>\n\n\n\n

How synthetic polls represent attitudes and opinions<\/h3>\n\n\n\n

On numerous questions in our surveys, our synthetic poll gave the appearance of a public that is far more lockstep \u2013 and often far more certain \u2013 in its attitudes than it actually is.<\/p>\n\n\n\n

A question about whether the United States or China benefits more from trade between the two countries is a good example. Our synthetic poll estimated that fully 98% of Americans think China benefits more from that relationship. That\u2019s 56 percentage points higher than the real share of U.S. adults who feel this way. It also obscures notable shares who feel that the U.S. benefits more (10%), who say both countries benefit equally (24%), and who say they aren\u2019t sure (19%).<\/p>\n\n\n\n

And on a series of questions about the changing influence of different countries on the global stage, the model tended to gravitate toward certain answer choices for no apparent reason. Our AI poll estimated that:<\/p>\n\n\n\n

    \n
  • 88% of Americans think India has been getting stronger in recent years (while the actual share is 30%).<\/li>\n\n\n\n
  • 77% say Canada has been getting weaker (actually 23%).<\/li>\n\n\n\n
  • 100% say China has been getting stronger (actually 62%).<\/li>\n\n\n\n
  • 92% say Iran\u2019s influence has stayed the same (actually 33%).<\/li>\n<\/ul>\n\n\n
    \t\t
    \n\t\t\t
    \t\t\t\t
    \n\t\t\t\t\t
    \t\t\t\t\t
    \n\t\t\t\t\t\t
    Synthetic respondents differ from real Americans on descriptors of Trump<\/strong><\/div>\n\t\t\t\t\t\t
    % who say each describes Donald Trump \u2026<\/em><\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t\t\n
    \n
    \"\"<\/figure>\n<\/div>\n\t\t\t\t\t\t\t\t\t\t
    \n\t\t\t\t\t\t
    Note: Figures for U.S. adults may differ slightly from those previously published by the Center because they are based on a subset of respondents to the original survey.<\/div>\n\t\t\t\t\t\t
    Source: Survey of U.S. adults and \u201cdigital twins\u201d synthetic analysis using Claude Opus 4.6 set to low reasoning with extended profile information and expert reflection. Survey was conducted April 20-26, 2026 (replicated April 27-May 1).
    \u201cCan AI Stand In for Human Survey-Takers? Not Really\u201d<\/div>\n\t\t\t\t\t\t
    PEW RESEARCH CENTER<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t\t
    \t\t\t\t<\/div>\n\t\t\t\t\t\t\t\n\t\t\t<\/div>\n\t\t\t\n\t\t\t\n\t\t\t\t
    \n\t\t\t\t\t
    \n\t\t\t\t\t\t

    Share this chart<\/h2>\n\t\t\t\t\t\t