esantus

fake news

The rise of fake news is everything but a recent phenomenon. It did not start with Donald Trump (or against him) and with Donald Trump it will certainly not end. The use of rumors and misinformation strategies to support political positions or attack rivals, probably dates back to the first human assemblement and certainly to the first gods. Despite such a long history, fake news became a major concern in recent years because of the easy amplification they obtain through social media (e.g. Facebook and Twitter).

With the advent of Artificial Intelligence, algorithms have been applied to the automatic creation and propagation of fake news. AI is however not only an enemy. In our project, we mostly deal with the purpose of identifying fake news by observing (1) how texts about the same topic diverge form each other, and (2) whether it is possible to fact-check the statements in those texts.

Our lab, in collaboration with the University of Pisa and the University of Udine, is developing neural models that exploit graphical representations and reinforcement learning to learn how to measure news divergence and automatically retrieve facts that may support or deny statements.

The final goal of our project is to promote informed reading by providing the readers with news confidence scores and supplemental material. Our tools are also expected to help journalists, who may use them to support their writing.

collaborators