Scalable Spatial Crowdsourcing: A study of distributed algorithms

Abstract — Recently spatial crowdsourcing was introduced as a natural extension to traditional crowdsourcing allowing for tasks to have a geospatial component, i.e., a task can only be performed if a worker is physically present at the location of the task. The problem of assigning spatial tasks to workers in a spatial crowdsourcing system can be formulated as a weighted bipartite b-matching graph problem that can be solved optimally by existing methods for the minimum cost maximum flow problem. However, these methods are still too complex to run repeatedly for an online system, especially when the number of incoming workers and tasks increases. Hence, we propose a class of approaches that utilizes an online partitioning method to reduce the problem space across a set of cloud servers to construct independent bipartite graphs and solve the assignment problem in parallel. Our approaches solve the spatial task assignment approximately but competitive to the exact solution. We experimentally verify that our approximate approaches outperform the centralized and MapReduce version of the exact approach with acceptable accuracy and thus suitable for online spatial crowdsourcing at scale. Keywords—distributed spatial task assignment; spatial task assignment; online partitioning; spatial crowdsouring I