A Campus-Scale Mobile Crowd-Tasking Platform

By effectively utilizing smartphones to reach out and engage a large population of mobile users, mobile crowd-sourcing can become a game-changer for many urban operations, such as last mile logistics and municipal monitoring. To overcome the uncertainties and risks associated with a purely best-effort, opportunistic model of such crowd-sourcing, we advocate a more centrally-coordinated approach, that (a) takes into account the predicted movement paths of workers and (b) factors in typical human behavioral responses to various incentives and deadlines. To experimentally tackle these challenges, we design, develop and experiment with a real-world mobile crowd-tasking platform on an urban campus in Singapore. In this paper, we first introduce TA$Ker and then demonstrate the effectiveness of different behavioral experiments, such as bundling and differential task pricing methods.