Task Assignment with Consensus Decision for Spatial Crowdsouring

Xiaomeng Lian, Wei He, Lizhen Cui, Hui Li, Lei Liu

Abstract: In recent years, spatial crowdsourcing has become a hot topic in both academic and industry community. In many spatial crowdsourcing scenarios, each task needs to be assigned to a certain number of workers, who are expected to complete the task in the required location and within the time limits. As acceptance and completion of crowdsourcing tasks are based on workers' voluntary basis, it's challenging to assign different tasks to a suitable group of workers who are willing to perform. In this paper, we propose a group-based task assignment model (GTAM) based on consensus decision strategies, which includes two phases: Worker Preference Modeling (WPM) and Group Preference Modeling(GPM). WPM is based on collaborative filtering to learn each worker's preference for different task categories and GPM utilizes the fuzzy preference matrix based on consensus decision-making to learn the group preferences of the workers. Finally, experiments are conducted to show the effectiveness and efficiency of the model.