A novel task recommendation model for mobile crowdsourcing systems

With the developments of sensors in mobile devices, mobile crowdsourcing systems are attracting more and more attention. However, how to recommend user-preferred and trustful tasks for users is an important issue to improve efficiency of mobile crowdsourcing systems. This paper proposes a novel task recommendation model for mobile crowdsourcing systems. Considering both user similarity and task similarity, the recommendation probabilities of tasks are derived. Based on dwell-time, the latent recommendation probability of tasks can be predicted. In addition, the trust of tasks is obtained based on their reputations and participation frequencies. Finally, we perform comprehensive experiments towards the Amazon metadata and YOOCHOOSE datasets to verify the effectiveness of the proposed recommendation model.