INCENTIVIZING RECRUITMENT THROUGH SOCIAL NETWORKS IN MOBILE CROWD SOURCING

Abstract

Worker recruitment stands as a critical challenge in the realm of mobile crowdsourcing (MCS), where the goal is to identify a sufficient and suitable pool of participants for task execution. While existing worker recruitment strategies predominantly concentrate on selecting the most appropriate workers from a vast pool, the specific issue of recruitment in scenarios with insufficient workers, such as in the inception of a new MCS system, has been inadequately addressed. This paper delves into the intricacies of the insufficient participation problem within MCS systems featuring a limited number of workers and proposes a innovative approach utilizing social networks to recruit workers and expand the worker pool.
Our solution, named SocialRecruiter, introduces a dynamic incentive mechanism to stimulate workers on the MCS platform to disseminate tasks through their social networks. This, in turn, encourages the invitation of friends to join the MCS platform, subsequently broadening the pool of available workers for task completion. Inspired by the SIR epidemic model, we present a task-specific epidemic model, offering a novel perspective to characterize the dynamic status changes of users engaged in task propagation and completion through social networks.
The proposed incentive mechanism operates by providing propagating rewards andcompleting rewards based on workers' actions, aiming to maximize task completion within budget constraints. Notably, to optimize task completion while managing
financial resources, the propagating and completing rewards are dynamically adjusted at each cycle in response to real-time worker recruitment progress. Extensive experimentation on two real-world datasets validates the efficacy of SocialRecruiter, demonstrating its superiority over state-of-the-art approaches in terms of worker recruitment and task completion.