Upgrade to Pro — share decks privately, control downloads, hide ads and more …

How ICIJ cracked the Panama and the Paradise Papers by Mar Cabra at Big Data Spain 2017

How ICIJ cracked the Panama and the Paradise Papers by Mar Cabra at Big Data Spain 2017

Leaked data is getting to journalists at a massive scale and they're too, using technology and big data techniques to expose wrongdoing and corruption, like in the Panama and Paradise Papers investigations.

https://www.bigdataspain.org/2017/talk/revolutionizing-investigative-journalism-with-open-data

Big Data Spain 2017
November 16th - 17th Kinépolis Madrid

Cb6e6da05b5b943d2691ceefa3381cad?s=128

Big Data Spain

November 29, 2017
Tweet

Transcript

  1. None
  2. None
  3. None
  4. None
  5. None
  6. None
  7. None
  8. None
  9. None
  10. None
  11. None
  12. None
  13. None
  14. None
  15. None
  16. None
  17. None
  18. None
  19. None
  20. None
  21. None
  22. None
  23. None
  24. None
  25. None
  26. None
  27. We got lucky! Thanks to tech Photo: 8ShroomFairy8

  28. Rigoberto Carvajal Emilia Díaz-Struck Cécile Schilis-Gallego Matthew Caruana Galizia Miguel

    Fiandor THE “PAPERS DATA SUPERHEROES” Jorge González Julien Martin Pierre Romera Manuel Villa Mar Cabra
  29. None
  30. None
  31. queue AWS machines extracting text from files with Ubuntu +

    Tesseract + Extract index
  32. The “Watergate-type reporter” Investigated the President (Paraguay) The developer Knows

    all about data (France) Skills Needs
  33. Investigative social networking

  34. Radical sharing

  35. +400 journalists

  36. Investigative e-discovery

  37. None
  38. None
  39. 4 journalists, 7 ½ years of their life

  40. None
  41. None
  42. Investigative graphs

  43. None
  44. None
  45. Interactive link

  46. https://offshoreleaks.icij.org

  47. None
  48. It’s not even the tip of the iceberg Photo: Ben

    O’Bryan
  49. TO DO • Entity extraction • Email pattern analysis •

    Content & data mining • Other leaks in data silos • Machine learning • Matches with other document collections • Alerts with real time news • Investigative recommendations • ...
  50. Photo: jessica Let’s stop playing bingo! Mar Cabra International Consortium

    of Investigative Journalists mcabra@icij.org