Happy to share the latest result of our #ArtificialIntelligenceLab . ( http://Recod.ai ) here at the Instituto de Computação – Unicamp , UNICAMP – Universidade Estadual de Campinas . This is a great collaboration with Antonio Theophilo and Université de Bordeaux ‘s Romain Giot.
Attributing the authorship of social media messages online is an ambitious endeavor; nevertheless, it is a way to fight the disinformation scenario. We tackle the problem of authorship attribution of tiny messages relying upon data-driven approaches, avoiding handcraft features, and harnessing recent advances of deep neural networks in the field of pattern recognition.
By modeling small texts employed in social media as unidimensional signals, we propose a deep learning model to project these messages onto a manifold suitable for the task of authorship attribution. We provide two state-of-the-art solutions tailored for different setups and strategies for the scenario of authorship verification.