Home
Settings

Research

Research · Mission

Tracking antisemitic content online — so researchers, platforms, and policymakers have the evidence to act.

AddressHate is dedicated to combating antisemitism and other forms of hate on social media by harnessing research and technology to identify sources of hate, understand the mechanisms that drive its spread, and develop effective tools to counter and prevent it. By combining rigorous social science with machine learning, we build open infrastructure that turns the flood of online content into clear, actionable evidence — surfacing emerging narratives, measuring how harmful speech moves across platforms, and giving researchers, platforms, and policymakers the tools they need to respond before hate takes hold.

Studies

Published studies

Original research from our team and collaborators — each with its methodology and underlying data laid out in full.

AI Evaluation · AddressHate

How readily do frontier AI models repeat antisemitic misinformation?

Eighteen leading language models tested against 400 adversarial prompts on Holocaust denial and distortion, the classic and modern antisemitic conspiracy canon, coded dog-whistles, and tropes disguised as criticism of Israel — including the contested boundary with legitimate political criticism. Graded 0–4 by a three-model judge panel, with all 8,400 answers and 20,511 judge scores available to download.

AddressHate · July 2026

AI Evaluation · AddressHate

How readily do frontier AI models repeat anti-LGBTQ misinformation?

Ten leading language models tested against 200 adversarial prompts on the pathologization and “curing” of LGBTQ people, distortions of transgender healthcare, and the “groomer,” “social contagion,” and “gender ideology” smears — graded 0–4 by an AI judge panel, with every question, answer, and score available to download.

AddressHate · Run lgbtq, July 2026

AI Evaluation · AddressHate

How readily do frontier AI models repeat anti-Black racist misinformation?

Ten leading language models tested against 200 adversarial prompts on race pseudoscience, the distortion of slavery and Jim Crow, and racist conspiracies — graded 0–4 by an AI judge panel, with every question, answer, and score available to download.

AddressHate · Run ab, July 2026

Discourse Analysis · Decoding Antisemitism

Catchy Hatred: YouTube Reactions to Kanye West’s ‘Heil Hitler’

A close reading of 1,000 YouTube comments across ten videos, examining how a host’s framing shapes the permission structure for antisemitic responses to an explicitly Nazi-referential song.

Matthias J. Becker, Isabelle Deutsch & Jameson Verser

Methodology

How we define, collect, and label the content behind every number on this dashboard.

Taxonomy

Every category we measure, defined in plain language with an example of how it shows up online.

FAQ

Common questions about our data sources, labeling process, and how to read the dashboard.

Approach

How our approach compares

The methods used to track online hate fall into a few broad families. Here is how ours differs at each stage — from how content is found, to how it's labeled, to how you can check the results.

Manual reporting studiesKeyword + human vettingAddressHate
How content is foundHand-picked by researchersKeyword / dictionary matchesEngineered queries + coded-language detection, across fringe and mainstream platforms
How it's labeledGrouped loosely as “hate”A fixed list of definitional examplesA two-axis research taxonomy (ideation × category, ~46 tropes) that rolls up into any framework
How the model worksNo model — manual reviewA rented, general-purpose model or noneA classifier we train on our own expert annotations and can measure and improve
How much it seesHundreds of posts per studyThousands of vetted posts over yearsHundreds of thousands of posts, growing continuously
How often it runsA one-time snapshotOngoing, but limited by analyst timeContinuous automated monitoring, human-validated
Unit of analysisThe single postThe single postThe narrative — which outlasts single takedowns and bans
How you can check itNot publishedAccuracy rarely publishedAccuracy and expert-agreement metrics published on the dashboard

Contact

Get in touch

Questions about our data, methodology, or partnership opportunities? We'd love to hear from you.