AddressHate offers an interdisciplinary diagnostics platform that continuously monitors public social‑media streams for antisemitic, racist, misogynistic and other forms of digital hate.
Funding
Funding not disclosed
Founders
Product
Problem
Online platforms see a rapid increase in hateful content, but organizations lack tools to detect, prioritize, and respond to such material in real time, leading to unchecked spread and harmful societal impacts.
Solution
AddressHate provides an interdisciplinary diagnostics platform that continuously monitors social media streams for antisemitic, racist, misogynistic, and other forms of digital hate. The system combines social‑science research, data‑science pipelines, and AI models to identify hateful posts, assess their severity, and flag them for intervention. Real‑time alerts and triage dashboards enable moderators, NGOs, and policy makers to act quickly, while integrated cultural and public‑health insights inform targeted counter‑measures. The platform’s shared infrastructure supports collaborative research and operational workflows, allowing stakeholders to measure the effectiveness of interventions and adapt strategies over time.
Target Audience
Primary users include social‑media platforms, NGOs, government agencies, and research institutions that need systematic, real‑time monitoring and response tools for digital hate.
Features
- Automated ingestion of public social‑media data with language‑agnostic hate detection algorithms
- Multi‑dimensional scoring that quantifies severity, target group, and potential reach of each hateful instance
- Real‑time alerting and triage interface for prioritizing high‑impact content
- Integrated analytics combining quantitative AI outputs with qualitative sociocultural context
- Collaborative workspace for researchers and practitioners to share findings, develop interventions, and track outcomes
- API access for embedding detection capabilities into existing moderation or monitoring systems