Link weight based truth discovery in social sensing

Abstract

This paper presents a link weight based maximum likelihood estimation framework to solve the truth discovery problem in social sensing applications. Social sensing has emerged as a new paradigm of data collection, where a group of individuals collect and share observations or measurements about the physical world at scale. A key challenge in social sensing applications lies in ascertaining the correctness of reported observations from unvetted data sources with unknown reliability. We refer to this problem as truth discovery. In this paper, we develop a new link weight based truth discovery scheme that solves the truth discovery problem by explicitly considering different degrees of confidence that sources may express on the reported data. The preliminary results show that our new scheme significantly outperforms the-state-of-the-art baselines and improves the accuracy of the truth estimation results in social sensing applications.