Skip to content

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.

Spread & networksPlatforms, policy & society Fear Doesn't Go Viral, It Lingers: Spread, Affect, and Discourse of Food-Fear Content on TikTokFear-based content about food on TikTok reaches fewer people than non-fear nutrition videos but sustains engagement and discussion far longer. Fear videos trigger more negative, angry, and disgusted comments that persist for weeks; their discourse concentrates on distrust of food industry, contamination, and institutional skepticism. Shin et al. · The Web Conference · 2027

Psychology & interventionsPlatforms, policy & society Do politics make us irrational?A 2013 study of 1,100 adults showed that political identity overrides mathematical ability: participants solved identical data-interpretation problems accurately when answers were neutral, but when the correct answer contradicted their political beliefs, even mathematically skilled participants failed. This partisan bias stems from… Van Bavel · 2026

Psychology & interventionsPlatforms, policy & society The dangers of the partisan brainOur brains are shaped by partisan identity to perceive reality differently, even when presented with identical evidence. Research shows that both liberals and conservatives reject factual information that contradicts their political beliefs—a phenomenon driven by motivated reasoning, structural differences in brain architecture, and… Van Bavel · 2026

Psychology & interventionsPlatforms, policy & society Can you outsmart a troll (by thinking like one)?Wardle uses a scenario-based approach to teach audiences how disinformation campaigns operate by role-playing as a malicious actor. The video demonstrates a real election disinformation strategy: creating fake accounts, spreading memes, exploiting confirmation bias to suppress opposing voters, making false voting claims, spreading… Wardle · 2026

Detection methodsPlatforms, policy & society Fake News Theories: Harnessing Disciplinary Insights for Computational Modeling, Detection, and ExplanationThis paper develops a theory-informed computational framework that translates cross-disciplinary social science theories into interpretable, measurable features for fake news detection. The authors systematically review theories from communication, psychology, and economics—organized into content-based, source-related, and network-level… Cao et al. · arXiv · 2026

Deepfakes & multimodalFact-checking & verification Presenting: The Bellingcat Online Open Source Investigations ToolkitBellingcat presents their newly restructured Online Open Source Investigations Toolkit, an AI-powered search interface that aggregates tools for digital verification and investigative research. The toolkit provides categorized access to resources for satellite imagery, social media analysis, transportation tracking, and source archiving,… Bellingcat · 2026

Platforms, policy & societySpread & networks Investigating Media Manipulation and DisinformationResearchers at Harvard Kennedy School present frameworks and practical tools for investigating online media manipulation. Joan Donovan introduces mediammanipulation.org's encyclopedia of manipulation tactics and a detailed case study of how the COVID lab-leak disinformation campaign exploited academic preprint archives. Donovan · 2026

Psychology & interventionsDetection methods Measuring and Reducing Misinformation SusceptibilityJon Roozenbeek presents two major contributions: (1) the Misinformation Susceptibility Test (MIST), a psychometrically validated 20-item measure of how well people distinguish true from false headlines, and (2) findings that video-based inoculation interventions teaching manipulation techniques significantly improve people's ability to… Roozenbeek · PERITIA Workshop · 2026

Platforms, policy & societySpread & networks Algorithmic Intervention Decreases Polarization in Content ModerationX's Community Notes transitioned from simple majority voting to a bridging algorithm that rewards agreement across ideologically diverse contributors. Comparing 8,805 notes and 4,367 contributors before and after this change (July 2021–September 2022), ideological polarization in both contributor and note positions decreased… Bertani et al. · arXiv · 2026

Deepfakes & multimodalLLMs & generative AI Detector-Guided Vocoder Training for Adversarial Text-to-Speech SynthesisThis paper presents a method to generate synthetic speech that evades deepfake detectors by integrating detector loss directly into vocoder training, rather than applying post-hoc perturbations. The approach fine-tunes a BigVGAN vocoder while freezing the acoustic model and detector, generating adversarial speech that retains high… Cui et al. · arXiv · 2026

Deepfakes & multimodalDetection methods ReplayFactor: Replay-Aware Dual-Attribute Learning for Practical Speech Deepfake DetectionExisting speech deepfake detectors fail on physically replayed synthetic speech (played through a loudspeaker and re-recorded), a low-cost, practical threat to voice authentication systems. ReplayFactor addresses this by learning both source authenticity (human vs. generated) and replay presence (non-replayed vs. replayed) via SSL-based… He et al. · arXiv · 2026

Deepfakes & multimodalDetection methods GraphSeal: Graph-Augmented Speech Deepfake Detection via Temporal-Spectral Artifact PropagationGraphSeal proposes a dynamic temporal-spectral graph neural network for speech deepfake detection that outperforms fixed-topology baselines on generalization tasks. Unlike prior graph-based anti-spoofing methods that use feature-extraction-determined topologies, GraphSeal constructs utterance-specific edges from both temporal adjacency… Lee et al. · arXiv · 2026

Fact-checking & verificationPlatforms, policy & society When Imperfect Automated Fact-Checking Backfires: Social Learning in the Presence of MisinformationAutomated fact-checking tools are free and fast but error-prone; manual checking is costly but accurate. This paper studies whether adding a free automated tool alongside manual fact-checking improves social welfare (defined as the probability a cascade reaches the correct conclusion). Liu & Cao · arXiv · 2026

Deepfakes & multimodalDetection methods CLRM: Cross-Layer Relation Modeling for Audio Deepfake DetectionAudio deepfake detection (ADD) distinguishes authentic speech from synthetic or manipulated speech. Existing methods either select informative layers from self-supervised learning (SSL) speech encoders or aggregate features across layers, but this discards useful variation in how different layers represent genuine vs. spoofed speech. Qu et al. · arXiv · 2026

Deepfakes & multimodalDetection methods UniGADD: Universal Generator-Agnostic Deepfake DetectorUniGADD proposes a two-stage supervised contrastive learning framework for detecting deepfakes from previously unseen generators. The method learns discriminative embeddings from known fake generators in stage one, then refines cluster structure via intra-cluster compactness constraints in stage two. Tomczyk et al. · arXiv · 2026

Deepfakes & multimodalDatasets & evaluation DeepfakeGenome: Toward Next-Generation Deepfake AttributionDeepfakeGenome (DFG) is a large-scale benchmark for deepfake detection and attribution covering 100 facial forgery algorithms and 2M images — 4–100× larger than prior benchmarks. The paper proposes 4 evaluation protocols using novel retrieval-based attribution metrics (mAP, Recall) instead of reject-class classification, and conducts… Wang et al. · NeurIPS 2026 · 2026

Deepfakes & multimodalDetection methods VeriSpoof: Beyond Real or Fake with One Audio LLMVeriSpoof is an audio language model system that unifies multiple forensic tasks in a single neural framework: detecting whether a speech recording is synthetic, identifying which generator produced it, analyzing recording conditions, and verifying whether two recordings share a source. The system achieves state-of-the-art results on… Xiao & Dang · Technical Report · 2026

LLMs & generative AIPlatforms, policy & society From Leniency to Suspicion: How an Open Post-Training Recipe Changes Whom LLM Fact-Checkers BelievePost-training can introduce social class bias into LLM-based fact-checkers: when the Tülu-3 open post-training recipe is applied to OLMo-2 32B, the model becomes more skeptical of claims from lower-status posters (service workers, manual laborers) while remaining lenient toward claims from higher-status posters (professionals,… AlDahoul & Zaki · arXiv · 2026

Bots & coordinated campaignsDatasets & evaluation Statistical Detectability of CoordinationThis paper formulates coordination detection as a hypothesis-testing problem on account pairs, modeling coordination as a planted submatrix. The authors derive statistical and computational detection limits, test four different null models on 26 information-operation datasets across 7 modalities, and show that multi-modal aggregation is… Iannucci et al. · arXiv · 2026

Detection methodsLLMs & generative AI Propasafe-Hybrid: A Text-Based Hybrid Propaganda Detection ToolPropasafe-Hybrid is a sentence-level propaganda detection tool that combines an offline BERT classifier with LLM-based technique identification. The hybrid architecture reduces API token usage (filtering 80–87% of sentences locally) while delivering interpretable technique labels and explanations at the point of consumption. Kimmeth et al. · arXiv · 2026

Spread & networksPlatforms, policy & society New Election, Same Old Story: How Tropes Form a Grammar of Election RumorsElection rumors follow recurring narrative patterns organized as a three-layer framework: meta-categories (actors, objects, actions, scenes, remedies) that combine into meso-tropes (villain, conspiracy, etc.), which manifest as micro-tropes (specific claims about mail voting, machines, etc.). Analysis of 590 rumors from 2020–2022 U.S.… Prochaska et al. · arXiv · 2026

LLMs & generative AIDatasets & evaluation The uneven rise of AI-generated web contentAnalyzing 5+ million webpages from 2019–2026, this work documents that AI-generated text prevalence rose from ~2% to nearly 25% by August 2026, with uneven adoption across the web. Growth is concentrated in peripheral, poorly-connected domains rather than central platforms; English-language and .com pages show higher prevalence than .edu… Visokay et al. · arXiv · 2026

Spread & networksDetection methods Where Does Rhetorical Distortion Live? A Multi-Platform, Multi-Language Measurement of Influencer ContentRhetorical distortion—misleading framing that inflates significance, manufactures anxiety, or misrepresents novelty—is not uniformly distributed across platforms or account types. This work measures five linguistic dimensions of distortion (Significance Inflation, Anxiety Manufacture, Novelty Claims, Loaded Language, Temporal Distortion)… Yu et al. · arXiv · 2026

Spread & networksDatasets & evaluation Friends as Sensors: High-Sensitivity Monitoring of Misinformation and Platform Dynamics via the Friendship ParadoxThe friendship paradox—a network property where a user's friends are, on average, better connected than the user themselves—enables high-sensitivity monitoring of misinformation on Twitter/X. Comparing ~27 million tweets from randomly selected users to ~31 million from accounts those users retweet (the "sensors"), the authors find: (1)… Angermaier et al. · arXiv · 2026