Trustworthy Crowdsourcing via Mobile Social Networks

Use of social network services has been more widespread as mobile social network applications have been developed for smart phones. Besides, smart phone sensing, namely Sensing-as-a-Service (S-2 aaS) provides the front-edge access to the cloud-centric Internet of Things. S-2 aaS can provide crowdsourced data for several purposes such as public safety, crowd management and environment monitoring. Trustworthiness of crowdsourced data is an important challenge in S-2 aaS as maliciously altered data can be misleading for the S-2 aaS customer. Reputation-aware crowdsourcing schemes can address trustworthiness problem however smart phone users moving based on a social network mobility (SNM) model introduce further challenges. In this paper, we propose reputation-and-SNM-aware crowdsourcing scheme which is based on an auction executed at a cloud platform. The cloud platform aims at maximum utility by estimating users' future locations based on their interactions over the social network service so that efficient user-sensing task matching can be done. Furthermore, past and current reputation of the users are taken into account while recruiting smart phone users for given sensing tasks. Our simulations show that reputation-awareness accompanied with SNM-awareness can significantly increase the platform utility by up to 55%. Furthermore, incorporation of reputation-awareness can degrade disinformation probability by more than 70%.