Truth discovery in crowdsourced detection of spatial...
Transcript of Truth discovery in crowdsourced detection of spatial...
![Page 1: Truth discovery in crowdsourced detection of spatial eventswouyang/slides/Truth_discovery_slides.pdf · location visit indicators, truth of events and three-way participant reliability](https://reader034.fdocuments.in/reader034/viewer/2022042806/5f6d78a1ed37375a01389929/html5/thumbnails/1.jpg)
Truth discovery in crowdsourced
detection of spatial events
Robin Wentao Ouyang
Mani Srivastava
Alice Toniolo
Timothy J. Norman
![Page 2: Truth discovery in crowdsourced detection of spatial eventswouyang/slides/Truth_discovery_slides.pdf · location visit indicators, truth of events and three-way participant reliability](https://reader034.fdocuments.in/reader034/viewer/2022042806/5f6d78a1ed37375a01389929/html5/thumbnails/2.jpg)
Mobile crowdsourced event detection
• Potholes, graffiti, bike racks, flora, …
2
![Page 3: Truth discovery in crowdsourced detection of spatial eventswouyang/slides/Truth_discovery_slides.pdf · location visit indicators, truth of events and three-way participant reliability](https://reader034.fdocuments.in/reader034/viewer/2022042806/5f6d78a1ed37375a01389929/html5/thumbnails/3.jpg)
Truth discovery
• Given crowdsourced detection reports with time and
loc tags, find which reported events are true and
which are false
3
![Page 4: Truth discovery in crowdsourced detection of spatial eventswouyang/slides/Truth_discovery_slides.pdf · location visit indicators, truth of events and three-way participant reliability](https://reader034.fdocuments.in/reader034/viewer/2022042806/5f6d78a1ed37375a01389929/html5/thumbnails/4.jpg)
Challenges
• Detection reports are non-conflicting
• Uncertainty in both participants’ reliability and
mobility
▫ Missing reports are ambiguous
• Supervision is difficult
4
![Page 5: Truth discovery in crowdsourced detection of spatial eventswouyang/slides/Truth_discovery_slides.pdf · location visit indicators, truth of events and three-way participant reliability](https://reader034.fdocuments.in/reader034/viewer/2022042806/5f6d78a1ed37375a01389929/html5/thumbnails/5.jpg)
Possible solutions
5
Severe privacy
and energy issues Trivial conclusion
Performance
degradation
![Page 6: Truth discovery in crowdsourced detection of spatial eventswouyang/slides/Truth_discovery_slides.pdf · location visit indicators, truth of events and three-way participant reliability](https://reader034.fdocuments.in/reader034/viewer/2022042806/5f6d78a1ed37375a01389929/html5/thumbnails/6.jpg)
Problem
6
Can we design an algorithm that can
reliably discover true events in mobile
crowdsourced event detection
but without location tracking and
supervision?
![Page 7: Truth discovery in crowdsourced detection of spatial eventswouyang/slides/Truth_discovery_slides.pdf · location visit indicators, truth of events and three-way participant reliability](https://reader034.fdocuments.in/reader034/viewer/2022042806/5f6d78a1ed37375a01389929/html5/thumbnails/7.jpg)
Proposed model
• Graphical model
• A participant’s likelihood of reporting an event
depends on
▫ 1) whether the participant visited the event location
▫ 2) whether the event at that location is true or false
▫ 3) how reliable the participant is
7
Location visit
indicator
Location
popularity
Participant
reliability
Event label Report
![Page 8: Truth discovery in crowdsourced detection of spatial eventswouyang/slides/Truth_discovery_slides.pdf · location visit indicators, truth of events and three-way participant reliability](https://reader034.fdocuments.in/reader034/viewer/2022042806/5f6d78a1ed37375a01389929/html5/thumbnails/8.jpg)
Proposed model
• Location popularity
▫ For each event at location
Draw the location’s popularity
8
![Page 9: Truth discovery in crowdsourced detection of spatial eventswouyang/slides/Truth_discovery_slides.pdf · location visit indicators, truth of events and three-way participant reliability](https://reader034.fdocuments.in/reader034/viewer/2022042806/5f6d78a1ed37375a01389929/html5/thumbnails/9.jpg)
Proposed model
• Participants Location visit indicators
▫ For participant and event at location
Draw a location visit indicator
• A participant has a higher chance to visit more
popular locations
9
Location visit
indicator
Location
popularity
![Page 10: Truth discovery in crowdsourced detection of spatial eventswouyang/slides/Truth_discovery_slides.pdf · location visit indicators, truth of events and three-way participant reliability](https://reader034.fdocuments.in/reader034/viewer/2022042806/5f6d78a1ed37375a01389929/html5/thumbnails/10.jpg)
Proposed model
• Event label
▫ For each event at location
Draw the event’s prior truth probability
Draw the event’s label
10
Location visit
indicator
Location
popularity
Event label
![Page 11: Truth discovery in crowdsourced detection of spatial eventswouyang/slides/Truth_discovery_slides.pdf · location visit indicators, truth of events and three-way participant reliability](https://reader034.fdocuments.in/reader034/viewer/2022042806/5f6d78a1ed37375a01389929/html5/thumbnails/11.jpg)
Proposed model
• Three-way participant reliability
▫ For each participant
Draw her true positive rate while present (TPR)
Draw her false positive rate while present (FPR)
Draw her reporting rate while absent (RRA)
• Concerns ▫ A participant’s reliability depends on: whether she visited the
event location and whether the event there is true or false
▫ A participant’s TPR and FPR may be asymmetric (reliable vs.
conservative participants)
▫ A participant must conform to physical constraints (RRA)
11
![Page 12: Truth discovery in crowdsourced detection of spatial eventswouyang/slides/Truth_discovery_slides.pdf · location visit indicators, truth of events and three-way participant reliability](https://reader034.fdocuments.in/reader034/viewer/2022042806/5f6d78a1ed37375a01389929/html5/thumbnails/12.jpg)
Proposed model
• Reports (detection = 1, missing = 0)
▫ For participant and event at location
12
TPR
FPR
RRA
Location visit
indicator
Location
popularity
Participant
reliability
Event label Report
![Page 13: Truth discovery in crowdsourced detection of spatial eventswouyang/slides/Truth_discovery_slides.pdf · location visit indicators, truth of events and three-way participant reliability](https://reader034.fdocuments.in/reader034/viewer/2022042806/5f6d78a1ed37375a01389929/html5/thumbnails/13.jpg)
Analysis
• 1) Missing reports are well explained
• When location popularity , we have
• When location popularity , we have
13
Event label &
participants’
TPR/FPR
Limited mobility &
participants’ RRA
![Page 14: Truth discovery in crowdsourced detection of spatial eventswouyang/slides/Truth_discovery_slides.pdf · location visit indicators, truth of events and three-way participant reliability](https://reader034.fdocuments.in/reader034/viewer/2022042806/5f6d78a1ed37375a01389929/html5/thumbnails/14.jpg)
Analysis
• 2) Location tracking is avoided.
▫ Location popularity is a collective rather than a
personal measure.
▫ Its prior counts need to be estimated only once.
▫ It can be jointly learned with other parameters
from data.
• 3) Different aspects of participant reliability are
handled.
• 4) Prior belief can be easily incorporated.
14
![Page 15: Truth discovery in crowdsourced detection of spatial eventswouyang/slides/Truth_discovery_slides.pdf · location visit indicators, truth of events and three-way participant reliability](https://reader034.fdocuments.in/reader034/viewer/2022042806/5f6d78a1ed37375a01389929/html5/thumbnails/15.jpg)
Experiments
• Methods in comparison ▫ MV (majority voting)
▫ TF (truth finder [1])
▫ GLAD (generative model of labels, abilities, and difficulties [2])
▫ LTM (latent truth model [3])
▫ EM (expectation maximization [4])
▫ TSE (truth finder for spatial events) – proposed
• [1] X. Yin, J. Han, and P. S. Yu. Truth discovery with multiple conflicting information providers on
the web. IEEE TKDE, 20(6):796–808, 2008.
• [2] J. Whitehill et al. Whose vote should count more: Optimal integration of labels from labelers of unknown expertise. In NIPS, pages 2035–2043, 2009.
• [3] B. Zhao et al. A bayesian approach to discovering truth from conflicting sources for data integration. VLDB Endowment, 5(6):550–561, 2012.
• [4] D. Wang et al. On truth discovery in social sensing: a maximum likelihood estimation approach. In IPSN, pages 233–244. ACM, 2012.
15
![Page 16: Truth discovery in crowdsourced detection of spatial eventswouyang/slides/Truth_discovery_slides.pdf · location visit indicators, truth of events and three-way participant reliability](https://reader034.fdocuments.in/reader034/viewer/2022042806/5f6d78a1ed37375a01389929/html5/thumbnails/16.jpg)
Experiments
• Traffic light detection • A mobility dataset
containing time-stamped
GPS location traces for
536 taxicabs in SF ▫ Spatial area of interest
3.5km x 4.4km
– further divided into two
subareas
▫ Temporal span 25 days
• Detection reports ▫ A participant waits for
15-120 seconds
16
![Page 17: Truth discovery in crowdsourced detection of spatial eventswouyang/slides/Truth_discovery_slides.pdf · location visit indicators, truth of events and three-way participant reliability](https://reader034.fdocuments.in/reader034/viewer/2022042806/5f6d78a1ed37375a01389929/html5/thumbnails/17.jpg)
Experiments
• Traffic light detection
17
![Page 18: Truth discovery in crowdsourced detection of spatial eventswouyang/slides/Truth_discovery_slides.pdf · location visit indicators, truth of events and three-way participant reliability](https://reader034.fdocuments.in/reader034/viewer/2022042806/5f6d78a1ed37375a01389929/html5/thumbnails/18.jpg)
Experiments
• Traffic light detection (Area 2)
18
![Page 19: Truth discovery in crowdsourced detection of spatial eventswouyang/slides/Truth_discovery_slides.pdf · location visit indicators, truth of events and three-way participant reliability](https://reader034.fdocuments.in/reader034/viewer/2022042806/5f6d78a1ed37375a01389929/html5/thumbnails/19.jpg)
Experiments
• Image-based event detection
19
![Page 20: Truth discovery in crowdsourced detection of spatial eventswouyang/slides/Truth_discovery_slides.pdf · location visit indicators, truth of events and three-way participant reliability](https://reader034.fdocuments.in/reader034/viewer/2022042806/5f6d78a1ed37375a01389929/html5/thumbnails/20.jpg)
Experiments
• Simulation (F1 score on event labels)
20
![Page 21: Truth discovery in crowdsourced detection of spatial eventswouyang/slides/Truth_discovery_slides.pdf · location visit indicators, truth of events and three-way participant reliability](https://reader034.fdocuments.in/reader034/viewer/2022042806/5f6d78a1ed37375a01389929/html5/thumbnails/21.jpg)
Experiments
• Simulation (MAE on TPRs a and FPRs b)
21
![Page 22: Truth discovery in crowdsourced detection of spatial eventswouyang/slides/Truth_discovery_slides.pdf · location visit indicators, truth of events and three-way participant reliability](https://reader034.fdocuments.in/reader034/viewer/2022042806/5f6d78a1ed37375a01389929/html5/thumbnails/22.jpg)
Discussion
• Sequential mobility modeling
• Dependent sources
• Cross-domain truth discovery
22
![Page 23: Truth discovery in crowdsourced detection of spatial eventswouyang/slides/Truth_discovery_slides.pdf · location visit indicators, truth of events and three-way participant reliability](https://reader034.fdocuments.in/reader034/viewer/2022042806/5f6d78a1ed37375a01389929/html5/thumbnails/23.jpg)
Conclusion
• Our proposed model integrates location popularity,
location visit indicators, truth of events and three-
way participant reliability in a unified framework.
• It can efficiently handling both unknown participants’
reliability and mobility.
• It can efficiently discover true events in mobile
crowdsourced event detection without any
supervision and location tracking.
23
![Page 24: Truth discovery in crowdsourced detection of spatial eventswouyang/slides/Truth_discovery_slides.pdf · location visit indicators, truth of events and three-way participant reliability](https://reader034.fdocuments.in/reader034/viewer/2022042806/5f6d78a1ed37375a01389929/html5/thumbnails/24.jpg)
Q & A
24