Hate, Quantified


Published on

Leveraging Hatebase’s open dataset for agencies and organizations

Published in: Technology, Spiritual
  • Be the first to comment

  • Be the first to like this

Hate, Quantified

  1. 1. Hate, quantified Leveraging Hatebase’s open dataset for agencies and organizations Timothy Quinn | The Sentinel Project for Genocide Prevention
  2. 2. Hatebase is a technology platform for monitoring and analyzing regionalized hate speech
  3. 3. Hatebase uses human and machine moderation to identify offline and online hate speech
  4. 4. Current dataset contains approx: Vocabulary Languages Sightings Countries Registered users API users 1,000 terms (including variants) * 70 12,000 150 250 50 * Plus a pending dataset expansion of 2,000 more terms Statistics as of August 2013
  5. 5. What is hate speech? Hate speech is difficult to quantify, but most people would agree with Justice Potter Stewart's famous sentiment: "I know it when I see it." Hatebase defines hate speech as any term which broadly categorizes a specific group of people based on malignant, qualitative, and/or subjective attributes -- particularly if those attributes pertain to ethnicity, nationality, religion, sexuality, disability, or class.
  6. 6. The Hatebase test for classifying hate speech 1. Does it refer to a specific group of people or is it a generalized insult? If the latter, it's probably not hate speech. 2. Can it potentially be used with malicious intent? If not, it's probably not hate speech. 3. Are there objective third-party sources online which can be used as citations? If not, it's probably not hate speech. 4. If you were to write a program which monitors hate speech on Twitter, would finding it in a random tweet be potentially meaningful? If not, it's probably not hate speech.
  7. 7. Hatebase is not... ...a wiki, lexicon, or online reference tool Hatebase is... ...a robust dataset which becomes most meaningful when normalized / contextualized ORGANIZATION-SPECIFIC DATA SIGHTINGS VOCABULARY
  8. 8. Hatebase can be used by government agencies, NGOs, and other organizations to: ● Monitor tensions across areas of concern ● Triage the distribution of human, material, and financial resources ● Respond appropriately and in a timely fashion to spikes in hate speech usage ● Perform long-term analysis on underlying causes and apply predictive results to future planning efforts
  9. 9. For example... Hatebase Data Crime Data Policy Data Economic Data Census Data Combining data from numerous datasets can help reveal important relationships between government, citizens and external actors.
  10. 10. RESEARCH Case study: The Sentinel Project for Genocide Prevention MEDIA MONITORING FIELDWORK HATEBASE THREATWIKI ANALYSIS EARLY WARNING CRISIS MITIGATION The Sentinel Project uses Hatebase data to contextualize its threat assessments of situations of concern (SOCs)
  11. 11. To access the Hatebase open API: 1. Create an account at hatebase. org 2. Review the FAQs to understand what data Hatebase collects and how Hatebase categorizes hate speech 3. Self-provision a unique and confidential API key 4. Review the API documentation and conditions of use* 5. Connect to the API using your own API key and specifying any appropriate filters * A usage cap applies to all API queries. Please inquire about unique implementations.
  12. 12. To learn more about Hatebase Visit the website: hatebase.org Read the FAQs: hatebase.org/faqs Check out The Sentinel Project: thesentinelproject.org Connect via social media: twitter.com/SentinelProject facebook.com/stopgenocide
  13. 13. Or read about us in: