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.

Adaptive Spatial Crowdsourcing leveraging Location-based Social Networks


Published on

Presented at SIGSPATIAL 2015.

This paper introduces the flag-verify-fix pattern that employs spatial crowdsourcing for city maintenance. The patterns motivates the need for appropriate assignment of dynamically arriving spatial tasks to a pool for workers on the ground. The assignment is aimed at maximizing the coverage of tasks spread over spatial locations; however, the coverage depends of willingness of workers to perform tasks assigned to them. We introduce the maximum coverage assignment problem that formulates two design issues of dynamic assignment. The quantity issue determines the number of worker required for a task and selection issue determines the set of workers. We propose an adaptive algorithm that uses location diversity based on a location-based social network to address the quantity issue and employs Thompson sampling for selecting the workers by learning their willingness. We evaluate the performance of the proposed algorithm in terms of coverage and number of assignments using real world datasets. The results show that our proposed algorithm achieves 30%-50% more coverage than the baseline algorithms, while requiring less workers per task.

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

  • Be the first to like this

Adaptive Spatial Crowdsourcing leveraging Location-based Social Networks

  1. 1. Adaptive Spatial Crowdsourcing leveraging Location-based Social Networks Umair ul Hassan, Edward Curry ACM SIGSPATIAL 2015 November 3-6, 2015 — Seattle, WA, USA
  2. 2. Motivation: Flag-Verify-Fix Pattern Spatial crowdsourcing for volunteered city maintenance Flag General public reports problems in their neighbourhood Verify Volunteer crowd workers verify reported problem Fix Volunteer crowd workers eradicate the problem
  3. 3. Problem: Adaptive Task Assignment Maximum Coverage Assignment Broadcast notification to all workers is an inefficient approach Quantity Issue Assign multiple workers to increase chances of task coverage How many workers should be assigned? Selection Issue Heterogeneous and reluctant workers Which set of workers should be assigned?
  4. 4. Quantity Issue: Location Diversity • Location-based social network for location entropy of a task • Number of workers
  5. 5. Selection Issue: Thompson Sampling Combinatorial Multi-armed Bandits (CMAB) Choose workers while learning their willingness over time Actual Willingness Estimated Willingness Ti: Total tasks assigned to so far Si: Complete tasks so fat
  6. 6. Results: DynTS Algorithm • Thompson sampling based algorithms have at least 30% more coverage • Location diversity results in at least 10% less assignments