Fighting fake news through phylogeny analysis

Abstract

The world is facing a new era in which social media communication plays a fundamental role in people's lives. Along with irrefutable benefits, several collateral drawbacks have risen, one being the wide spread of false information with malicious intents, what is now commonly called "Fake News". The fight against this problem is not easy, especially when taking into account the nature of text messages involved on social media platforms (a sea of small messages and myriad users). In this vein, this research project aims to address the important and difficult problem of phylogeny analysis of small text messages posted on social media platforms, showing how this solution can help in the identification of false information spread on social networks. Differently from what has been done with longer texts, we will rely upon data-driven approaches, exploiting recent advances of deep neural networks in the fields of Natural Language Processing and pattern recognition. Using Deep Learning techniques for language modeling, we will develop a synthetic dataset to train novel machine learning classifiers over a graph representation of near-duplicate texts, two scientific contributions expected from this work. By trying to solve an ever-growing problem of our society, this research will produce outcomes that can be used by many actors. For example, social media platforms could directly apply the techniques developed to bring higher reliability and also transparency to the published data. People, in general, could also deploy them to verify the accuracy of the information posted on social networks and news portals. Moreover, this research can provide appropriate tools to achieve another level of understanding regarding online posts, taking into consideration their spread and power of influence. (AU)