TTAF: A two-tier task assignment framework for cooperative unit-based crowdsourcing systems

Traditional task assignment follows a direct recruitment model in which requesters recruit and select workers to complete tasks. Because of the unclear division of roles and the diversity of each role's mission, this model is neither efficient nor scalable. This paper introduces the concept of cooperative unit (CU), in which workers are organized into cooperative units, whose proxies bid for tasks from requesters based on worker characteristics. However, because of the decentralization of task assignment, quality control is complicated, and the benefits of different roles must be balanced. As a result, we propose a novel two-tier task assignment framework (TTAF) that produces high-quality results while striking the appropriate balance between requesters, CUs, and workers. We first propose a vector-based expertise representation model that evaluates workers' expertise based on previous answers. Then, we devise a higher-tier task assignment between tasks and CUs that maximizes answer quality while staying within budget. The quality of the answers is ensured by aspects such as keyword coverage, overall expertise, and the number of workers. We also devise lower-tier task assignment, which evenly distributes tasks among workers such that more workers have the opportunity to perform tasks. The extensive evaluation shows that our proposed approaches achieve promising results.