Abstract
Crowdsourcing is an approach where requesters can call for workers with different capabilities to process a task for monetary reward. With the vast amount of tasks posted every day, satisfying workers, requesters, and service providers--who are the stakeholders of any crowdsourcing system--is critical to its success. To achieve this, the system should address three objectives: (1) match the worker with a suitable task that fits the worker's interests and skills, and raise the worker's rewards; (2) give requesters more qualified solutions with lower cost and time; and (3) raise the accepted tasks rate which will raise the aggregated commissions accordingly. For these objectives, we present a critical study of the state-of-the-art in recommendation systems that are ubiquitous among crowdsourcing and other online systems to highlight the potential of the best approaches which could be applied in a crowdsourcing system, and highlight the shortcomings in the existing crowdsourcing recommendation systems that should be addressed.