Explore everything
Filter by research area, year and venue. Every filter is in the address bar, so you can share a view as a link.
Datasets & evaluationFact-checking & verification
Are You a Racist or Am I Seeing Things? Annotator Influence on Hate Speech Detection on TwitterThis paper compares hate speech detection systems trained on expert annotations (from feminist and anti-racism activists) versus amateur annotations (crowdsourced via CrowdFlower) on 6,909 tweets. Systems trained on expert annotations significantly outperform those trained on amateur data, and amateur annotators systematically label more…
Bots & coordinated campaignsDetection methods
DNA-Inspired Online Behavioral Modeling and Its Application to Spambot DetectionProposes a novel methodology to characterize online user behavior using DNA-inspired digital sequences, where each user action (tweet type, content features) is encoded as a character in a string. Applies standard bioinformatic DNA analysis techniques—specifically longest common substring (LCS) analysis—to detect spambots on Twitter by…
Bots & coordinated campaignsDatasets & evaluation
BotOrNot: A System to Evaluate Social BotsBotOrNot is a publicly available service and API that evaluates whether a Twitter account is controlled by a human or automated bot. Using 1,000+ features across six categories (network, user, friends, temporal, content, sentiment), the system applies Random Forest classification to achieve 0.95 AUC on a labeled dataset of 15k bots and…
Spread & networksPlatforms, policy & society
Reducing Controversy by Connecting Opposing ViewsThis paper proposes an algorithmic approach to reduce polarization on social media by recommending social connections (edges) between opposing sides. Using an endorsement graph representation and the random-walk-based controversy metric, the authors formulate the problem as k-edge-addition and develop an efficient algorithm (ROV) that…
Spread & networksPlatforms, policy & society
Corporate funding and ideological polarization about climate changeFarrell analyzes 40,785 texts (39+ million words) from 164 climate contrarian organizations between 1993–2013, employing Structural Topic Modeling and social network analysis to demonstrate that corporate funding from entities like ExxonMobil and Koch family foundations directly influences which polarization themes are created and…
Fact-checking & verificationPlatforms, policy & society
Boundaries Not Drawn: Mapping the institutional roots of the global fact-checking movementGraves maps the institutional landscape of 64+ fact-checking organizations globally across two summits (2014–2015), using ethnographic fieldwork and ternary plots to sort organizations along three axes: journalism, academia, and politics/civil society. The movement has a journalistic core but exhibits striking institutional diversity and…
Bots & coordinated campaignsDetection methods
The Rise of Social BotsSocial bots—automated software agents in social media—are increasingly sophisticated and pose real threats including misinformation spread, trend manipulation, and election interference. This paper characterizes modern bot behavior, surveys detection challenges, and proposes a taxonomy of detection approaches: graph-based methods…
Platforms, policy & societyPsychology & interventions
In Related News, That Was Wrong: The Correction of Misinformation Through Related Stories Functionality in Social MediaThis study tests whether Facebook's "related stories" feature can correct misinformation by exposing users to debunking information. Two experiments (students and Mechanical Turk workers) examined vaccine-autism and GMO-illness misperceptions.
Detection methodsFact-checking & verification
Fact Checking: Task definition and dataset constructionThis paper introduces fact-checking as a formal computational task: assessing the truthfulness of political claims as an ordinal classification problem with five labels (TRUE, MOSTLYTRUE, HALFTRUE, MOSTLYFALSE, FALSE). The authors construct a dataset of 106 objectively-verifiable fact-checked statements from PolitiFact and Channel 4 (out…
Spread & networksDatasets & evaluation
Rumor CascadesFriggeri et al. tracked thousands of rumors on Facebook using Snopes.com as ground truth, finding that rumor cascades run deeper in the social network than typical content. True rumors spread more virally than false ones despite false rumors being more frequently uploaded; Snopes fact-checks increase deletion likelihood for false rumors…
Spread & networksDetection methods
Can Cascades be Predicted?Information cascades on social networks can be predicted with reasonable accuracy (~80%) using temporal and structural features extracted from early observations. Performance improves substantially as more cascade stages are observed.
Psychology & interventionsFact-checking & verification
Misinformation and Its Correction: Continued Influence and Successful DebiasingThis comprehensive review synthesizes literature on why false beliefs persist despite corrections, examining cognitive mechanisms (coherence, credibility, source confusion, fluency) that render misinformation resistant to change. The authors propose evidence-based debiasing strategies—warnings, alternative explanations, repeated…
Detection methodsSpread & networks
Information Credibility on TwitterThis paper proposes supervised learning classifiers to automatically assess the credibility of news discussed on Twitter. Using human-labeled topics from trending discussions, the authors extract message-level, user-level, topic-level, and propagation-level features to build classifiers that distinguish newsworthy from conversational…
Spread & networksDatasets & evaluation
The structure and function of complex networksThis comprehensive review surveys the properties and mathematical models of complex networks across diverse domains: social networks, the Internet, biological networks, and collaboration networks. Newman covers observed structural properties (degree distributions, clustering, small-world effects), foundational models (random graphs,…
Spread & networksPsychology & interventions
A Theory of Fads, Fashion, Custom, and Cultural Change as Informational CascadesFoundational theoretical framework explaining how fads, fashions, and beliefs spread through sequential information cascades: when individuals use others' actions to infer information while ignoring their own private signals, widespread adoption of incorrect beliefs and practices can occur.
Psychology & interventionsDetection methods
Why People Fall for MisinformationJoseph Isaac traces how misconceptions persist using the tongue map myth as exemplar: David Hänig's 1901 research found modest taste-sensitivity variations across tongue regions, but through translation barriers, visual simplification, and our preference for clean narratives, it became the false claim that sweetness is imperceptible at…
Spread & networksDetection methods
Climate Change Misinformation: Supply, Demand, and the Challenges to ScienceLewandowsky examines climate denial through supply and demand lenses: well-funded disinformation campaigns (billions annually from fossil fuel interests and conservative think tanks) deploy cherry-picked data to infiltrate mainstream media and political rhetoric, while political ideology (conservatism, libertarianism) predisposes people…
Psychology & interventionsPlatforms, policy & society
How to Pre-Bunk Misinformation and DisinformationJon Roozenbeek discusses psychological inoculation as a scalable defense against misinformation. Rather than focusing on veracity (which becomes politically contested), he proposes teaching people to recognize predictable manipulation techniques before encountering false content.
Spread & networksBots & coordinated campaigns
The Spread of Misinformation in Social MediaMenczer presents a framework for understanding misinformation spread through social networks as an inevitable consequence of network structure and human cognitive limitations rather than platform design failures. He discusses how structural properties—scale-free topology, finite attention, information overload—create vulnerabilities…
Psychology & interventionsDetection methods
Towards psychological herd immunity: Cross-cultural prebunking against COVID-19 misinformationJon Roozenbeek presents a cross-cultural randomized controlled trial testing two psychological interventions against COVID-19 misinformation. Comparing the "Go Viral" game (technique-based inoculation) against UNESCO infographics and a Tetris control condition across 1,777 participants in the UK, Germany, and France, he demonstrates that…
Spread & networksPlatforms, policy & society
Network PropagandaBenkler presents research on media asymmetry during the 2016 U.S. election, revealing that the right-wing media ecosystem operates under a fundamentally different structure than the center and center-left press. Rather than technological systems (Facebook algorithms, Russian interference) or individual-level factors, the key driver of…
Deepfakes & multimodalDetection methods
The Erosion of Shared Reality in the Age of DeepfakesGenerative AI has moved from nascent to commodity in just 18 months; text-to-image, text-to-video, and real-time interactive deepfakes are now trivial to create. Humans are bad at detecting them (performing ~60% accuracy on trained tasks vs. 50% chance).
Psychology & interventionsPlatforms, policy & society
The Misinformation AgeFalse beliefs persist and spread through social factors—conformity, institutional curation of evidence, and network structure—rather than individual cognitive biases alone. O'Connor examines historical cases (variolation in 18th-century England, tobacco industry strategy) and mathematical models to show how unbiased actors (journalists,…
Platforms, policy & societyFact-checking & verification
How Polarization Can Help Solve the Misinformation ProblemDavid Rand presents a counter-intuitive argument: while polarization is widely viewed as exacerbating misinformation, it may actually improve crowd-sourced fact-checking systems like Twitter's Birdwatch/Community Notes. Rather than a traditional technology approach (machine learning classifiers), platforms can scale fact-checking by…