Social user role value analysis and trusted user autonomous diffusion for participatory crowdsensing

Abstract

Social participatory-sensing, as an emerging research field, is extremely challenging to recruit trustworthy and active high-value users in a sparse user context. And the richness and closeness of users' social relationships provide new research ideas. Therefore, a participatory sensing user recruitment method based on dynamic social network role detection (DSRD) is proposed, in which firstly, multiple identity information of users is mined based on the decomposition of their overlapping social relationships to filter out high-quality sensing users. Secondly, based on role-oriented network representation learning, it models users' role information and establishes a role hierarchy model to evaluate users' social functions and role values. Finally, the concept of temporal social centrality is proposed for the first time for integrating users' social and network structural features to assess the overall value of users and ensure the coverage of task assignments under a sparse user pool. Experimental results on the open datasets Gowalla and Brightkite show that under the constraints of cost budget and number of users, the proposed user recruitment framework DSRD effectively improves task coverage with less time overhead compared to the baseline algorithm.