Explore papers
Filter by research area, year and venue. Every filter is in the address bar, so you can share a view as a link.
Platforms, policy & societySpread & networks
Social media and vaccine hesitancyLarge-scale cross-national analysis finds that social media use to organize offline action predicts public vaccine safety skepticism, while foreign disinformation campaigns significantly reduce vaccination coverage year-over-year. A one-point increase on the five-point disinformation scale correlates with a two-percentage-point drop in…
Fact-checking & verificationPsychology & interventions
Fact-Checking: A Meta-Analysis of What Works and for WhomMeta-analysis of 30 studies on fact-checking effectiveness finds modest but significant positive effects (d = 0.29) on belief correction. However, effects are substantially moderated by motivated reasoning, political ideology, message design, and context: pro-attitudinal fact-checking works better than counter-attitudinal corrections,…
Deepfakes & multimodalPlatforms, policy & society
Deepfakes and Disinformation: Exploring the Impact of Synthetic Political Video on Deception, Uncertainty, and Trust in NewsExperimental study (N=2,005 UK respondents) testing how political deepfakes affect deception and trust in news. Deepfakes increased uncertainty about content, and that uncertainty mediated reduced trust in news on social media.
Spread & networksPlatforms, policy & society
Causes and consequences of mainstream media dissemination of fake news: literature review and synthesisWhile fake news websites have limited direct reach, mainstream media coverage is probably how most people encounter fake news stories. This synthesis identifies why mainstream outlets cover falsehoods (journalists' professional duties, news values, peer psychology, technical infrastructure) and explores how mainstream coverage amplifies…
Spread & networksPlatforms, policy & society
Online misinformation about climate changeComprehensive literature review examining climate change misinformation from multiple disciplinary angles. Defines misinformation vs. disinformation, identifies networks of actors (scientists, governments, industry, media) spreading false claims, examines how social media characteristics (homophily, echo chambers, algorithmic bias)…
Psychology & interventionsPlatforms, policy & society
Susceptibility to misinformation about COVID-19 around the worldAn international survey of 3,750 adults across five countries (UK, Ireland, USA, Spain, Mexico) measured susceptibility to COVID-19 misinformation and examined how it predicts public health behaviors. While majorities in each country did not find COVID-19 misinformation credible, higher susceptibility to misinformation was strongly…
Psychology & interventionsPlatforms, policy & society
Fighting COVID-19 Misinformation on Social Media: Experimental Evidence for a Scalable Accuracy-Nudge InterventionTwo pre-registered experiments with 1,700+ U.S. adults show that a simple accuracy nudge — asking people to rate the accuracy of an unrelated headline before the main task — nearly tripled their ability to discriminate true from false COVID-19 headlines when deciding what to share on social media. The intervention is scalable, requires…
Bots & coordinated campaignsPlatforms, policy & society
Troll Factories: Manufacturing Specialized Disinformation on TwitterLinvill and Warren analyze 9.04 million tweets from Russia's Internet Research Agency (IRA) spanning 2009–2018, identifying five specialized account categories—Right Troll, Left Troll, News Feed, Hashtag Gamer, and Fearmonger—each with distinct behavioral patterns, temporal deployment strategies, and communication styles. The authors…
Fact-checking & verificationPlatforms, policy & society
Fact-checking as risk communication: the multi-layered risk of misinformation in times of COVID-19COVID-19 misinformation should be viewed as a risk in its own right, not just a communication failure. Fact-checking efforts face three key challenges: defining misinformation differently across political subgroups, earning trust in an environment of low press credibility, and communicating amid genuine uncertainty.
Psychology & interventionsPlatforms, policy & society
A digital media literacy intervention increases discernment between mainstream and false news in the United States and IndiaA randomized experiment tests Facebook's "Tips to Spot False News" intervention in the US and India, finding it increases discernment between mainstream and false news (26.5% in US, 17.3% in India online). The intervention reduces belief in false headlines more than it reduces belief in mainstream ones.
Bots & coordinated campaignsPlatforms, policy & society
Cross-Platform State Propaganda: Russian Trolls on Twitter and YouTube during the 2016 U.S. Presidential ElectionThis paper analyzes 1,052 Russian IRA Twitter accounts to understand their propaganda strategy during the 2016 U.S. presidential election. By examining hyperlinks to news stories and YouTube videos, the authors find IRA accounts linked to conservative sources more frequently than liberal ones, consistent with supporting Trump.
Bots & coordinated campaignsSpread & networks
It takes a village to manipulate the media: coordinated link sharing behavior during 2018 and 2019 Italian electionsCoordinated networks of Facebook pages and groups substantially amplified problematic news during Italian elections: coordinated entities shared problematic domains 1.79×–2.22× more frequently than uncoordinated ones. The paper introduces a method to detect "coordinated inauthentic behavior" by identifying entities that…
Psychology & interventionsSpread & networks
Misinformation and Morality: Encountering Fake-News Headlines Makes Them Seem Less Unethical to Publish and ShareFour preregistered experiments (N=2,587) show that repeatedly encountering fake-news headlines reduces moral condemnation of spreading them—regardless of whether people believe them. This "moral repetition effect" operates via fluency: familiar headlines feel less unethical to share, stronger inclinations to promote them online, and…
Bots & coordinated campaignsPlatforms, policy & society
Assessing the Russian Internet Research Agency's impact on the political attitudes and behaviors of American Twitter users in late 2017Combining longitudinal survey data from 1,239 partisan Twitter users with nonpublic IRA account data, Bail et al. find no evidence that interaction with Russian Internet Research Agency accounts substantially impacted six measures of political attitudes (affective/ideological polarization) or behaviors (political engagement, network…
Spread & networksPlatforms, policy & society
Evaluating the fake news problem at the scale of the information ecosystemUsing nationally representative data on mobile, desktop, and TV consumption spanning 2016–2018, the authors show that fake news comprises only 0.15% of Americans' daily media diet, while TV dominates news consumption by a 5:1 ratio over online. The paper challenges the widespread narrative of fake news as a pervasive crisis and suggests…
Spread & networksDetection methods
Fake news propagation and detection: A sequential modelFoundational sequential social learning model of misinformation spread and fact-checking. Introduces the framework for analyzing how agents' decisions cascade through a network and how fact-checking affects collective outcomes.
Spread & networksPlatforms, policy & society
Influence of fake news in Twitter during the 2016 US presidential electionUsing 171 million tweets from the five months preceding the 2016 U.S. election, this study found that 25% of news-sharing tweets contained fake or extremely biased content. Network analysis revealed distinct clusters of fake, biased, and mainstream news spreaders.
Platforms, policy & society
The platform governance triangle: conceptualising the informal regulation of online contentThis paper applies Abbott and Snidal's "governance triangle" framework to analyze how state actors, technology firms, and civil society organizations informally regulate online content through voluntary standards, codes of conduct, and multistakeholder initiatives. The analysis maps the European platform governance landscape, showing how…
Datasets & evaluationDetection methods
Predicting the Type and Target of Offensive Posts in Social MediaThis paper introduces OLID (Offensive Language Identification Dataset), a large-scale dataset of 14,100 English tweets annotated with a three-level hierarchical schema for detecting offensive content. The hierarchy distinguishes offensive from non-offensive posts (Level A), categorizes offense type as targeted insults or untargeted…
Spread & networksPlatforms, policy & society
Auditing Radicalization Pathways on YouTubeFirst large-scale quantitative audit of user radicalization on YouTube. The authors tracked 349 channels across three ideological communities (Intellectual Dark Web, Alt-lite, Alt-right) and found strong evidence that users systematically migrate toward more extreme content.
Bots & coordinated campaignsDeepfakes & multimodal
Characterizing the Use of Images in State-Sponsored Information Warfare Operations by Russian Trolls on TwitterLarge-scale analysis of 1.8M images posted by ~3.6K Russian state-sponsored Twitter accounts (IRA-controlled). Russian trolls strategically deployed images and memes to maximize political influence, with political imagery 2+ times more effective than general content.
Bots & coordinated campaignsDatasets & evaluation
Arming the public with artificial intelligence to counter social botsThis paper reviews social bot types, their impact on online discourse, and detection methods, then presents Botometer as a case study in how detection tools are used and interpreted by the public. The authors conducted a user experience survey (731 participants) revealing that while users find the tool useful, they struggle with…
LLMs & generative AIDetection methods
Automatic Detection of Generated Text is Easiest when Humans are FooledIppolito et al. investigate the complementary abilities of humans and machines to detect machine-generated text from GPT-2 under various decoding strategies. They find that fine-tuned BERT detectors outperform humans (achieving 80%+ accuracy on long excerpts versus 71% for expert human raters), but detector performance is highly…
LLMs & generative AIDetection methods
GLTR: Statistical Detection and Visualization of Generated TextGehrmann et al. present GLTR, a visual tool for detecting AI-generated text by analyzing statistical anomalies in language model output. The key insight is that language models sample from the head of the distribution (high-probability words), whereas humans use a wider vocabulary including low-probability choices.