6533b862fe1ef96bd12c611d

RESEARCH PRODUCT

What Are the Latest Fake News in Romanian Politics? An Automated Analysis Based on BERT Language Models

subject

description

Social media and news outlets facilitate information sharing, while the Web is flooded by information posted online on a daily basis. However, content may be differently transmitted from case to case, based on the authors’ intentions and vocabulary, to the extent that it generates completely opposite points of view. As such, fake news have become a global phenomenon, and recent events highlight a high impact of distorted or fake information, especially on the political side, when candidates’ discourses include tendentious statements that require careful validation before completely trusting the source. This paper proposes an automated analysis of political statements in Romanian by applying different state-of-the-art Natural Language Processing techniques, and evaluating the importance of context in determining their veracity. Our corpus consists of entries from Factual, a recent Romanian fact-checking initiative that assembled a list of public statements, alongside relevant contextual information for their interpretation. Our results are comparable to similar experiments performed on the PolitiFact dataset, and represent a strong baseline for experiments in low-resource languages, like Romanian.