Multimedia Crowdsourcing With Bounded Rationality: A Cognitive Hierarchy Perspective

In multimedia crowdsourcing, the requester's quality requirements and reward decisions will affect the workers' task selection strategies and the quality of their multimedia contributions. In this paper, we present a first study on how the workers' bounded cognitive rationality interacts with and affects the decisions and performance of a multimedia crowdsourcing system. Specifically, we consider a two-stage model, where a requester first determines the reward and the quality requirement for each task, and the workers select the tasks to accomplish accordingly. First, we consider the benchmark case where users are fully rational, and derive the requester's optimal rewards and quality requirements for the tasks. Furthermore, we focus on the more practical bounded rational case by modeling the workers' task selection behaviors using the cognitive hierarchy theory. Comparing with the fully rational benchmark, we show that the requester can increase her profit by taking advantage of the workers' bounded cognitive rationality, especially when the workers' population is large or the workers' average cognitive level is low. When the workers' average cognitive level is very high, however, the equilibrium under the practical bounded rational model converges to that under the benchmark fully rational model. It is because the workers at different levels make decisions sequentially and high cognitive level workers can accurately predict other users' strategies. Under both the fully and bounded rational models, we show that if workers are heterogeneous but one type of workers (either the high or the low quality) dominates the platform, the requester cannot make a higher profit by setting different quality requirements for different tasks.