Facebook’s Hate Speech Detection Algorithms Allegedly Disproportionately Failed to Remove Racist Content towards Minority Groups

November 21, 2021

Study reveals Facebook’s hate-speech detection algorithms under-reported less common but harmful content, disproportionately impacting minority groups such as Black, Muslim, LGBTQ, and Jewish users. This underscores the need for responsible AI governance and improved harm prevention measures.

Join us in shaping Project Cerebellum’s mission to establish guardrails for AI, utilizing our HISPI Project Cerebellum TAIM (Govern) database to address these issues and promote safe and secure AI practices. JOIN US

Matched TAIM controls

Suggested mapping from embedding similarity (not a formal assessment). Browse all TAIM controls

MAP 1.6 — similarity 0.638, rank 1. TAIM detail and related incidents →
MEASURE 2.10 — similarity 0.637, rank 2. TAIM detail and related incidents →
MAP 5.1 — similarity 0.636, rank 3. TAIM detail and related incidents →

Alleged deployer: facebook
Alleged developer: facebook
Alleged harmed parties: facebook-users-of-minority-groups, facebook-users

Source

Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/163

Data source

Incident data is from the AI Incident Database (AIID).

When citing the database as a whole, please use:

McGregor, S. (2021) Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database. In Proceedings of the Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (IAAI-21). Virtual Conference.

Pre-print on arXiv · Database snapshots & citation guide

We use weekly snapshots of the AIID for stable reference. For the official suggested citation of a specific incident, use the “Cite this incident” link on each incident page.