DejaVu: A Google Chrome Extension to Help Combat Visual Misinformation

Help journalists to search, check and annotate visual misinformation on the internet (deploying Deep Learning model in production)


This project was built for the Social Technologies Lab at Cornell Tech


Academic Paper: DejaVu: A System for Journalists to Collaboratively Address Visual Misinformation

  • Streamline the reverse image search process
  • Index and search social media sources
  • Support collaborative image annotation

DejaVu System Architecture



Background Information:

According to First Draft, there exist seven types of mis- and disinformation on the internet:

  1. Satire of Parody: No intention to cause harm but has potential to fool
  2. False Connection: When headlines, visuals or captions don't support the content
  3. Misleading Content: Misleading use of information to frame an issue or individual
  4. False Context: When genuine content is shared with false contextual information
  5. Imposter Context: When genuine sources are impersonated
  6. Manipulated Content: When genuine information or imagery is manipulated to deceive
  7. Fabricated Content: New content is 100% false, designed to deceive and do harm

Why Is This Type Of Content Being Created?





Sketches:




Figma Prototype:




Demo: