PHEME – Computing Veracity Across Media, Languages, and Social Networks
Start 2014.01.01, Finish 2017.03.31
A good reputation is hard-won and easily lost. Every other day we see how information and news affect every level of our society: Company stocks, sovereign debt, politicians. This fact is especially true in the Internet era where rumours go viral. The new research project Pheme, co-funded by the European Union’s ICT FP7 programme, aims to compute veracity of rumours across media, languages, and social networks.
Contact: Georgi Georgiev
The Pheme project will create a computational framework for automatic discovery and verification of information at scale and fast. This framework will allow a better understanding the impact of rumours in social media: where they originate, how they spread, who and why spreads them, with multiple uses in many domains. Pheme started in January 2014 and will be running over the course of three years. The Pheme consortium consists of 9 European partners from England, Germany, Austria, Spain, Bulgaria, Switzerland and Kenya. It is co-ordinated by the University of Sheffield.
Ontotext participates in a core role by providing a LOD-based reasoning about rumours, i.e. a domain-independent model of the four kinds of rumours addressed: misinformation, disinformation, unverified information, and disputed information. Modelling and reasoning about rumours is particularly challenging as it is necessary to represent multiple possible truths (e.g. superfoods may cause vs. prevent cancer) and to take into account the temporal validity of information, in other words to accommodate the possibility that two otherwise contradictory statements can be both valid at different points in time.
Moreover, Ontotext’s GraphDB™ knowledge base will be adapted as a semantic repository with scalable light-weight reasoning. Knowledge from relevant Linked Open Data (LOD) resources will be used, such as Ontotext’s FactForge, DBpedia, OpenCyc, and Ontotext’s LinkedLifeData. These datasets will provide invaluable large-scale world-knowledge of meronymy, synonymy, antonymy, hypernymy, and functional relations, all of which are essential features for classifying entailment and contradictions.