Monitoring hate speech with data-driven alert system
Challenge
The Research, Strategy and Analytics team of UNHCR’s Global Communications Service has developed a model that classifies hateful content in English targeting forcibly displaced people. This partial solution needs to be operationalized to systematize and automate data collection.
Solution
A user-friendly web application that tracks, visualizes and catalogues hateful social activities almost in real-time to facilitate analysis and alert key stakeholders via established communication channels when crises are identified.
Impact
Improved hate speech detection and response within UNHCR in accordance with the organization’s data protection standards, allowing UNHCR and its humanitarian partners to better understand hateful activities online and prevent discrimination against displaced people.
Project impact
Other information
Online hate speech against refugees is rising globally, yet UNHCR had no systematic way to detect, monitor or respond to it. Funded by the Data Innovation Fund and developed with UN Global Pulse, OHCHR, and academic partners, this project built hatefree.unhcr.org, an AI-powered platform combining natural language processing and human review to identify harmful content targeting forcibly displaced people across social media. The tool was piloted in two of the world's most sensitive displacement contexts, the Rohingya situation in Asia and the Venezuelan and Haitian displacement crises in the Americas – and was built with strong data protection safeguards. It equips UNHCR protection, communications and advocacy teams to counter xenophobia and inform safer digital spaces for refugees worldwide.
In May 2024, the project received global media attention, including a feature in El País profiling the tool and its impact on protecting refugees online. Read that story here.