“Half the Truth is often a great Lie.”
– Benjamin Franklin
PennMAP
Penn Media Accountability Project
PennMAP is an interdisciplinary, nonpartisan research project of the Computational Social Science Lab at the University of Pennsylvania dedicated to enhancing media transparency and accountability at the scale of the entire information ecosystem.
Touchstone Publications
Quantifying partisan news diets in Web and TV audiences
Evaluating the fake news problem at the scale of the information ecosystem
Measuring the news and its impact on democracy
Examining radical content consumption on YouTube
Data Dashboard: YouTube Politics
Does YouTube’s video recommendation algorithm drive users towards more extreme political content?
YouTube is arguably the largest and most engaging online media consumption platform in the world. Recently, its scale has fueled concerns that YouTube users are being radicalized via a combination of biased recommendations and ostensibly apolitical “anti-woke” channels, both of which have been claimed to direct attention to radical political content.
We test this hypothesis using a representative panel of over 300,000 Americans and their individual-level browsing behavior, on and off of the YouTube platform. Learn more with our interactive data dashboard.
Mission
Misinformation in media is believed to have harmful effects on public opinion, political polarization, and ultimately democratic decision making. And yet, much remains unknown regarding the prevalence of misinformation and its effects on society.
To address this problem, PennMAP is building technology to detect patterns of bias and misinformation in media from across the political spectrum and spanning television, radio, social media, and the broader web. We will also track consumption of information via television, desktop computers, and mobile devices, as well as its effects on individual and collective beliefs and understanding.
In collaboration with our data partners, we are also building a scalable data infrastructure to ingest, process, and analyze tens of terabytes of television, radio, and web content, as well as representative panels of roughly 100,000 media consumers over several years. While our initial focus is on the U.S., our hope is to scale this infrastructure to eventually cover other countries and languages other than English.
Commitment to Use-Inspired Research
We will share our insights through publications and interactive data visualizations, and will work with various stakeholders—including journalists, policy makers, and industry partners—to implement solutions. Aside from powering our own research, our infrastructure will support other research teams, thereby accelerating the pace of knowledge accumulation and enhancing its reliability.
In the News
Joe Biden’s (but not Donald Trump’s) age: A case study in the New York Times’ inconsistent narrative selection and framing
On the weekend of March 2-3, 2024, the landing page of the New York Times was dominated by coverage of their poll showing voter concern over President Biden’s age. There was a lot of concern among Democrats about the methods of the poll, especially around the low response rate and leading questions. But as a team of researchers who study both survey methods and mainstream media, we are not surprised that people are telling pollsters they are worried about Biden’s age. Why wouldn’t they? The mainstream media has been telling them to be worried about precisely this issue for months.
Hyperpartisan consumption on YouTube is shaped more by user preferences than the algorithm
Given the sheer amount of content produced every day on a platform as large as YouTube, which hosts over 14 billion videos, the need for some sort of algorithmic curation is inevitable. As YouTube has attracted millions of views on partisan videos of a conspiratorial or radical nature, observers speculate that the platform’s algorithm unintentionally radicalizes its users by recommending hyperpartisan content based on their viewing history.
But is the algorithm the primary force driving these consumption patterns, or is something else at play?
The YouTube Algorithm Isn’t Radicalizing People
About a quarter of Americans get their news on YouTube. With its billions of users and hours upon hours of content, YouTube is one the largest online media platforms in the world.
In recent years, there has been a popular narrative in the media that videos from highly partisan, conspiracy theory-driven YouTube channels radicalize young Americans and that YouTube’s recommendation algorithm leads users down a path of increasingly radical content.
In the News
Joe Biden’s (but not Donald Trump’s) age: A case study in the New York Times’ inconsistent narrative selection and framing
Hyperpartisan consumption on YouTube is shaped more by user preferences than the algorithm
The YouTube Algorithm Isn’t Radicalizing People
Warped Front Pages
The Unintended Consequence of Deplatforming on the Spread of Harmful Content
Radicalization at a Glance: Penn Media Accountability Project Launches Interactive Data Dashboard
People
Duncan Watts
Stevens University Professor
Penn Integrates Knowledge Professor
Homa Hosseinmardi
Associate Research Scientist
Amir Ghasemian
Affiliate Research Scientist
Yale University
David Rothschild
Affiliate Research Scientist
Microsoft Research
Coen Needell
Pre-Doctoral Researcher
Timothy Dorr
Ph.D. in Communications
Upasana Dutta
Ph.D. in Computer and Information Science
Samar Haider
Ph.D. in Computer and Information Science
Baird Howland
Ph.D. in Communications
Sam Wolken
Ph.D. in Communications and Political Science
People
Duncan Watts
Stevens University Professor
Penn Integrates Knowledge Professor
Homa Hosseinmardi
Associate Research Scientist
Amir Ghasemian
Affiliate Research Scientist
Yale University
David Rothschild
Affiliate Research Scientist
Microsoft Research
Coen Needell
Pre-Doctoral Researcher
Timothy Dorr
Ph.D. in Communications
Upasana Dutta
Ph.D. in Computer and Information Science
Samar Haider
Ph.D. in Computer and Information Science
Baird Howland
Ph.D. in Communications
Sam Wolken
Ph.D. in Communications and Political Science
Publications
Deplatforming did not decrease Parler users’ activity on fringe social media Journal Article
In: PNAS Nexus, vol. 2, iss. 3, 2023.
Quantifying partisan news diets in Web and TV audiences Journal Article
In: Science Advances, vol. 8, iss. 28, 2022.
Reducing opinion polarization: Effects of exposure to similar people with differing political views Journal Article
In: Proceedings of the National Academy of Sciences, vol. 118, no. 52, 2021.
Success stories cause false beliefs about success Journal Article
In: Judgment and Decision Making, vol. 16, no. 6, pp. 1439-1463, 2021, ISSN: 1930-2975.
Comparing Estimates of News Consumption from Survey and Passively Collected Behavioral Data Journal Article
In: Public Opinion Quarterly, 2021.
Examining the consumption of radical content on YouTube Journal Article
In: Proceedings of the National Academy of Sciences, vol. 118, no. 32, 2021.
Research note: Examining potential bias in large-scale censored data Journal Article
In: Harvard Kennedy School (HKS) Misinformation Review, 2021.
Measuring the news and its impact on democracy Journal Article
In: Proceedings of the National Academy of Sciences, vol. 118, no. 15, 2021.
Evaluating the fake news problem at the scale of the information ecosystem Journal Article
In: Science Advances, vol. 6, no. 14, pp. eaay3539, 2020.
Understanding Cyberbullying on Instagram and Ask.fm via Social Role Detection Journal Article
In: Companion Proceedings of The 2019 World Wide Web Conference, pp. 183-188, 2019.
Evaluating overfit and underfit in models of network community structure Journal Article
In: IEEE Transactions on Knowledge and Data Engineering, vol. 32, no. 9, pp. 1722-1735, 2019.
The science of fake news Journal Article
In: Science, vol. 359, no. 6380, pp. 1094-1096, 2018.
Beyond Keywords: Tracking the evolution of conversational clusters in social media Journal Article
In: Sociological Methods & Research, vol. 48, no. 3, pp. 588-607, 2017.