Multiple Cooperative Task Assignment on Reliability-Oriented Social Crowdsourcing

With the rapid development of mobile devices, mobile social networks have drawn increasing attention from spatial crowdsourcing in which users sharing information via social networking applications can easily identify and participate in multiple cooperative tasks. Existing studies generally assume that all users are trustworthy and can reliably perform assigned tasks. However, such assumptions do not hold in real-world practices. In this article, we consider an essential crowdsourcing problem, namely Reliability-oriented Socially-Aware Crowdsourcing (R-SAC), which improves the reliability by recruiting users who are better matched to the tasks. Our R-SAC problem is to recruit reliable users for multiple cooperative tasks so that the overall reliability of task assignment is maximized. We prove that the R-SAC problem is
$\mathcal {NP}$
-hard. Then, we propose an approximation algorithm with a factor of
$\ln {m} + 1$
to solve the R-SAC problem, where
$m$
is the number of tasks. Specifically, user reliability refers to the probability that a user can reliably perform assigned tasks. To achieve reliable user recruitment during task assignment, we formulate the reliability of a user by combining the matching between the user and tasks, and the reliability feedback from neighbors who share similar behaviors with the user in the social network. Besides, the distributed collaborative filtering technique is utilized to select the reliability feedback from the neighbors. We evaluate the performance of our proposed approach experimentally on two widely-used real-world datasets and the results demonstrate that our approach significantly outperforms five representative approaches.