VERA

Abstract

Social networks and the Web in general are characterized by multiple information sources often claiming conflicting data values. Data veracity is hard to estimate, especially when there is no prior knowledge about the sources or the claims and in time-dependent scenarios where initially very few observers can report first information. Despite the wide set of recently proposed truth discovery approaches, "no-one-fits-all" solution emerges for estimating the veracity of on-line information in open contexts. However, analyzing the space of conflicting information and disagreeing sources might be relevant, as well as ensembling multiple truth discovery methods. This demonstration presents VERA, a Web-based platform that supports information extraction from Web textual data and micro-texts from Twitter and estimates data veracity. Given a user query, VERA systematically extracts entities and relations from Web content, structures them as claims relevant to the query and gathers more conflicting/corroborating information. VERA combines multiple truth discovery algorithms through ensembling returns the veracity label and score of each data value and the trustworthiness scores of the sources. VERA will be demonstrated through several real-world scenarios to show its potential value for fact-checking from Web data.