FakeFlow: Fake News Detection by Modeling the Flow of Affective Information

Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, pages 679–689 April 19 - 23, 2021. ©2021 Association for Computational Linguistics 679 FakeFlow: Fake News Detection by Modeling the Flow of Affective Information Bilal Ghanem1, Simone Paolo Ponzetto2, Paolo Rosso1, Francisco Rangel3 1Universitat Polit`ecnica de Val`encia, Spain 2University of Mannheim, Germany 3Symanto Research, Germany bigha@doctor.upv.es, simone@informatik.uni-mannheim.de, prosso@dsic.upv.es, francisco.rangel@symanto.com Abstract Fake news articles often stir the readers’ atten- tion by means of emotional appeals that arouse their feelings. Unlike in short news texts, au- thors of longer articles can exploit such affec- tive factors to manipulate readers by adding ex- aggerations or fabricating events, in order to affect the readers’ emotions. To capture this, we propose in this paper to model the flow of affective information in fake news articles us- ing a neural architecture. The proposed model, FakeFlow, learns this flow by combining topic and affective information extracted from text. We evaluate the model’s performance with sev- eral experiments on four real-world datasets. The results show that FakeFlow achieves su- perior results when compared against state-of- the-art methods, thus confirming the impor- tance of capturing the flow of the affective in- formation in news articles. 1 Introduction In today’s information landscape, fake news are used to manipulate public opinion (Zhou and Za- farani, 2018) by reshaping readers’ opinions re- garding some issues. In order to achieve this goal, authors of fake news’ narratives need to capture the interest of the reader. Thus, they are putting efforts to make their news articles look more objective and realistic. This is usually done by adding misleading terms or events that can have a negative or positive impact on the readers’ emotions. Short text false information, e.g., fake claims or misleading headlines, might be less harmful than news articles. They may have some eye-catching terms that aim to manipulate the readers’ emotions (Chakraborty et al., 2016). In many cases, the iden- tification of this kind of exaggeration in short state- ments can unmask the fabrication. On the other hand, in fake news articles the authors exploit the length of the news to conceal their fabricated story. This fact exposes the readers to be emotionally manipulated while reading longer texts that have several imprecise or fabricated plots. The flow of information has been investigated for different tasks: Reagan et al. (2016) studied the emotional arcs in stories in order to understand complex emo- tional trajectories; Maharjan et al. (2018) model the flow of emotions over a book and quantify its usefulness for predicting success in books; Kar et al. (2018) explore the problem of creating tags for movies from plot synopses using emotions. Unlike previous works (Rashkin et al., 2017; Shu et al., 2018; Castelo et al., 2019; Ghanem et al., 2020) that discarded the chronological order of events in news articles, in this work we propose a model that takes into account the affective changes in texts to detect fake news. We hypothesize that fake news has a …

Content truncated to 500 words