A Multi-label Classification System to Distinguish among Fake, Satirical, Objective and Legitimate News in Brazilian Portuguese

Resumo

Currently, there has been a significant increase in the diffusion of fake news worldwide, especially the political class, where the possible misinformation that can be propagated, appearing at the elections debates around the world. However, news with a recreational purpose, such as satirical news, is often confused with objective fake news. In this work, we decided to address the differences between objectivity and legitimacy of news documents, where each article is treated as belonging to two conceptual classes: objective/satirical and legitimate/fake. Therefore, we propose a DSS (Decision Support System) based on a Text Mining (TM) pipeline with a set of novel textual features using multi-label methods for classifying news articles on these two domains. For this, a set of multi-label methods was evaluated with a combination of different base classifiers and then compared with a multi-class approach. Also, a set of real-life news data was collected from several Brazilian news portals for these experiments. Results obtained reported our DSS as adequate (0.80 f1-score) when addressing the scenario of misleading news, challenging the multi-label perspective, where the multi-class methods (0.01 f1-score) overcome by the proposed method. Moreover, it was analyzed how each stylometric features group used in the experiments influences the result aiming to discover if a particular group is more relevant than others. As a result, it was noted that the complexity group of features could be more relevant than others.