The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
Crowdsourcing satellite imagery (Talk at Giscience2012)
1. Crowdsourcing satellite imagery:
study of iterative vs. parallel models
Nicolas Maisonneuve, Bastien Chopard
Twitter: nmaisonneuve
Friday, September 21, 12 1
4. Organizational challenges:
How to organize non-trained volunteers,
especially to enforce quality?
Friday, September 21, 12 4
5. Organizational challenges:
How to organize non-trained volunteers,
especially to enforce quality?
Investigated scope:
• Qualitative + Quantitative study of 2 collaborative models inspired by
Computer science: iterative vs parallel information processing
• Controlled experiment to isolate quality = F(organisation), removing
other parameters e.g. training, task difficulty
• this research != studying real world collaborative practices but more
extreme/symbolic cases to guide collaborative system designers
Friday, September 21, 12 5
6. Organizational challenges:
How to organize non-trained volunteers,
especially to enforce quality?
Investigated scope:
• Qualitative + Quantitative study of 2 collaborative models inspired by
Computer science: iterative vs parallel information processing
• Controlled experiment to isolate quality = F(organisation), removing
other parameters e.g. training, task difficulty
• this research != studying real world collaborative practices but more
extreme/symbolic cases to guide collaborative system designers
Friday, September 21, 12 6
7. Organizational challenges:
How to organize non-trained volunteers,
especially to enforce quality?
Investigated scope:
• Qualitative + Quantitative study of 2 collaborative models inspired by
Computer science: iterative vs parallel information processing
• Controlled experiment to isolate quality = F(organisation), removing
other parameters e.g. training, task difficulty
• this research != studying real world collaborative practices but more
extreme/symbolic cases to guide collaborative system designers
Friday, September 21, 12 7
8. Tested Collaborative Models (1/2)
iterative model
e.g. wikipedia, open street map, assembly lines
Friday, September 21, 12 8
9. Tested Collaborative Models (2/2)
parallel model
aggregation
e.g. voting systems in society, distributed computing
Friday, September 21, 12 9
10. Tested Collaborative Models (2/2)
parallel model
old version (17th to mid 20th century): when computers were human/women
(Mathematical Table project - (1938 -1948)
Friday, September 21, 12 10
11. Qualitative comparison
Iterative Parallel
problem No need to divide complex Complex problem need to be
divisibility problem divided in easier pieces
Friday, September 21, 12 11
12. Qualitative comparison
Iterative Parallel
problem No need to divide complex Complex problem need to be
divisibility problem divided in easier pieces
optimization copy emphasizing isolation emphasizing
tradeoff exploitation exploration
Friday, September 21, 12 12
13. Qualitative comparison
Iterative Parallel
problem No need to divide complex Complex problem need to be
divisibility problem divided in easier pieces
optimization copy emphasizing isolation emphasizing
tradeoff exploitation exploration
quality redundancy + diversity of
sequential improvement
mechanism opinions
Friday, September 21, 12 13
14. Qualitative comparison
Iterative Parallel
problem No need to divide complex Complex problem need to be
divisibility problem divided in easier pieces
optimization copy emphasizing isolation emphasizing
tradeoff exploitation exploration
quality redundancy + diversity of
sequential improvement
mechanism opinions
useless redundancy for
path dependency effect +
side effect obvious decisions + pb of
sensitivity to vandalism
aggregation
Friday, September 21, 12 14
15. Controlled Experiment: web platform
Interface/instruction for the Parallel model
Friday, September 21, 12 15
16. on 3 maps with different topologies
(annotated by 1 UNITAR expert)
Friday, September 21, 12 16
17. Participants used for the experiments:
Mechanical Turk as simulator
Friday, September 21, 12 17
18. Data Quality Metrics
Quality of the collective output
• type I errors = p(wrong annotation)
• type II errors = p(missing a building)
• Consistency
Analogy with the information retrieval field:
• Precision = p(an annotation is a building)
• Recall = p(a building is annotated)
• F-measure = score mixing recall + precision
• (metrics adjusted with tolerance distance)
Friday, September 21, 12 18
19. Methodology for parallel model
Step 1 - collecting independent contribution:
N for (map1, map2, map3) = (121,120,113)
Friday, September 21, 12 19
20. Methodology for parallel model
Step 2 - for each map,
generating the set of groups of m=[1 to N] participants
m=1
m=2
m=3
Friday, September 21, 12 20
21. Methodology for parallel model
Step 3 - for each group: aggregating + computing quality
groups
of m = 2
Spatial Clustering of points + quorum
Compute Data Quality with Gold Standard
Precision Recall F-measure
Friday, September 21, 12 21
22. The more = the better?
(parallel model)
avg. F-measure
yes but until some points..
• (Adding more people wont change the consensus panel)
• Limitation of Linus’ law (compared to iterative model e.g.
openstreetmap)
• Wisdom != skill: we can’t replace training by more people
Friday, September 21, 12 22
24. Methodology for Iterative model
n instances
of about m
iterations
Collected data for map1, map2, map3 = 13, 21,25
instances of about 10 iterations
Friday, September 21, 12 24
25. Methodology for Iterative model
Step 2- for each iteration, we compute the precision,
recall, f-measure of all the instances
Precision Recall F-measure
Friday, September 21, 12 25
26. Intrepretation of results / Comparison
on data quality
Parallel Iterative
Accuracy -
wrong consensual results (*) error propagation
annotations
accumulation of
Accuracy -
useless redundancy on knowledge driving
missing
obvious buildings attention on
buildings
uncovered area
Consistency redundancy naive last = best
(*) but parallel < iterative in difficult cases (map 2) (lack of consensus)
Friday, September 21, 12 26
27. Side-objective: Measuring how the crowd spatially agrees
Method: taking randomly 2 participants and measure their
spatial inter-agreement (e.g. ratio of points matching) and repeat
the process N time
Friday, September 21, 12 27
28. Side-objective: Measuring how the crowd spatially agrees
Method: taking randomly 2 participants and measure their
spatial inter-agreement (e.g. ratio of points matching) and repeat
the process N time
way to measure the intrinsic difficulty of a task
(map 1 = easy , map 2 = quite hard)
Friday, September 21, 12 28
29. future tracks
Impact of the organization beyond data
quality
• Energy / Footprint to collectively solve a problem,
• Participation sustainability,
• On Individual behavior (skill Learning & Enjoyment)
Skill complementarity:
Is the best group of 3 people the best 3 people at the
individual level? data says no!
Other symbolic organisations / mechanism:
• human cellular automata (cell = 1 person, resubmit a task at
time t, because influenced by peers results generated at time
t-1)
• Integration of Game design / Gamification
Friday, September 21, 12 29