PHEME : computing veracity : the fourth challenge of big social data

Abstract

The veracity of information spreading through social media can sometimes be hard to establish and the deliberate or accidental spread of false information, especially during natural disasters or emergencies, is quite common. We coined the term phemes to describe fast spreading memes which are enhanced with truthfulness information. The PHEME project (http://www.pheme.eu) attempts to identify in real-time four kinds of phemes: controversy, speculation, misinformation and disinformation. This brings challenges in modelling the social network spread of and the online conversations around phemes; developing rumour detection methods; and using historical data to model trustworthiness of the information source.