Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Wids 2019

8 views

Published on

Talk given for Women in Data Science event in Zurich on 5th April 2019 about using crowdsourced data and interpreting the biases within

Published in: Data & Analytics
  • Be the first to comment

  • Be the first to like this

Wids 2019

  1. 1. The role of innovative data collection methods in advancing understanding, and the importance of considering the biases within. Dr Reka Solymosi @r_solymosi Reka.Solymosi@Manchester.ac.uk
  2. 2. Lecturer in quantitative methods Centre for Criminology University of Manchester “New” forms of data @r_solymosi
  3. 3. • Recall • Interviewer bias • Spatial resolution @r_solymosi
  4. 4. Harnessing information and skills from large crowds into one collaborative project. @r_solymosi
  5. 5. @r_solymosi
  6. 6. @r_solymosi
  7. 7. @r_solymosi
  8. 8. @r_solymosi
  9. 9. @r_solymosi
  10. 10. @r_solymosi
  11. 11. @r_solymosi
  12. 12. What’s in a name? @r_solymosi
  13. 13. Gender Anon: 66.8% Male: 24.4% Female: 8.6% @r_solymosi
  14. 14. @r_solymosi
  15. 15. @r_solymosi
  16. 16. @r_solymosi
  17. 17. Neighbourhood(?) guardianship @r_solymosi
  18. 18. @r_solymosi
  19. 19. @r_solymosi
  20. 20. @r_solymosi
  21. 21. @r_solymosi
  22. 22. @r_solymosi
  23. 23. @r_solymosi
  24. 24. @r_solymosi
  25. 25. CAUTION! @r_solymosi
  26. 26. Mode of production • Involved/ interested citizens • Pareto principle (++) @r_solymosi
  27. 27. @r_solymosi
  28. 28. @r_solymosi
  29. 29. Ethical consideration • Privacy/ surveillance • Data ownership • Data linkage • Implications of findings (service slanting) @r_solymosi
  30. 30. Possible solutions? Weighting? Small area estimation? Creative ways to make use of biases @r_solymosi
  31. 31. Thank you! Questions? @r_solymosi reka.solymosi@manchester.ac.uk

×