Statistical Claim Checking: StatCheck in Action

Abstract

To strengthen public trust and counter disinformation, computational fact-checking, leveraging digital data sources, attracts interest from the journalists and the computer science community. A particular class of interesting data sources is statistics, that is, numerical data compiled mostly by governments, administrations, and international organizations. Statistics typically are multidimensional datasets, where multiple dimensions characterize one value, and the dimensions may be organized in a hierarchy. We developed StatCheck, a fact-checking system specialized in French. The technical novelty of StatCheck is twofold: (i) we focus on multidimensional, complex-structure statistics, which have received little attention so far, despite their practical importance; and (ii) novel statistical claim extraction modules for French, an area where few resources exist. We will demonstrate our system on large statistic datasets (hundreds of millions of facts), including the complete INSEE (French) and Eurostat (European Union) datasets. More information about StatCheckis available online at: https://team.inria.fr/cedar/projects/statcheck/.