Improving Automated Fact-Checking Through the Semantic Web

The Internet supplies information that can be used to automatically populate knowledge bases and to keep them updated, but the facts contained in these automatically managed knowledge bases must be validated before being trustfully used by applications. So far, this process, known as fact-checking, has been performed by humans curators with experience in the investigated domain, however, the big increase of the speed to which the internet provides information makes this way of doing inadequate. Nowadays techniques exist for automatic fact-checking, but they lack on modeling the domain of the information to be checked, thus losing the experience feature humans curators provide. This work designs a Semantic Web platform for automatic fact-checking, which uses OWL Ontology to create a specific knowledge base modeled on the domain concerning the facts to be checked, and it extends the knowledge available by linking this knowledge base to external repository of information and by reasoning about this extended knowledge. The fact-checking task is performed using a machine learning algorithm trained using the information of this extended knowledge base.