Crowdsourcing has been widely adopted in various domains for problem-solving, idea generation and data collection, leveraging distributed networks for efficient outcomes. Crowdsourcing platforms harness workers’ collective productivity by assigning tasks to a diverse pool of workers. However, all these tasks are assigned to registered high-quality workers on the platform, which is prone to task congestion. Moreover, the mechanical scheduling of workers ignores workers’ productivity fluctuations, and fails to make full use of the productivity of high-quality workers who are not currently online. In order to solve these problems, we design a Self-organizing Collaborative Crowdsourcing Framework (SoCCF) to support worker collaboration. Specifically, we propose a two-stage strategy, including a Reputation-driven Collaborative Partner Selection (RCPS) algorithm to expand the pool of collaborative workers and a Lyapunov optimization-based Task Acceptance and Sub-Delegation (LTASD) algorithm to guide worker to make workload decisions that meet emotional needs. Extensive experiments based on simulated crowdsourcing scenarios demonstrate that SoCCF consistently achieves higher overall service utility, while ensuring that workers can achieve 90.2% of the benefits of traditional algorithms with only 82.5% effort on average.

The increasing popularity of crowdsourcing has resulted in the emergence of multiple crowdsourcing service providers (CSPs), such as Mechnical Turk and Crowdflower, which compete to attract crowd workers (CWs). CWs can share their experience working for various CSPs, which forms the basis of CSP reputation score. This information can be used for trust building and facilitating future CWs’ decisions on which CSP to work for. Existing reputation management research in crowdsourcing has mainly focused on controlling task quality and improving revenue from the perspective of CSPs. Little attention has been paid to helping CSPs manage their reputation to attract and retain CWs. In this paper, we propose the Crowdsourcing Service Provider Reputation Management (CSP-RM) framework to bridge this important gap. Based on the current reputation of CSPs, it dynamically balances the trade-off between the reputation maintenance cost and the long-term profit for a given CSP. It performs dynamic commission allocation for a CSP based on Lyapunov optimization to guide the recruitment of CWs, while considering the revenue and the changes in the number of CWs. Extensive experiments based on highly competitive crowdsourcing market demonstrate that CSP-RM makes the most advantageous cost-benefit trade-off compared to existing approaches, outperforming the best baseline by 23.83%, 39.21% and 3.36% in terms of average cumulative revenue, average number of CWs and public reputation, respectively. To the best of our knowledge, it is the first decision support framework for enabling CSPs to recruit more CWs in a highly competitive market, while maintaining their reputation and ensuring long-term benefit.