Meta-Learning for Fake News Detection Surrounding the Syrian War

Abstract

In this manuscript, we pursue the automatic detection of fake news reporting on the Syrian war using machine learning and meta-learning. Our model is based on a suite of features that include a given article's linguistic style, its level of subjectivity, sensationalism and sectarianism, the strength of its attribution, as well as its consistency with other news articles from the same ``media camp'' and reporting on the same single large-scale event detected from a timeline of the Syrian war. To train our model, we use FA-KES, a fake news dataset about the Syrian war, consisting of 804 articles roughly balanced between true and fake . We explore a suite of basic machine learning models as well as the model-agnostic meta-learning algorithm (MAML) suitable for few-shot learning, using datasets of a modest size. Our feature importance analysis confirms that our collection of features specific to the Syrian war are indeed very important predictors for the output label. Our meta-learning model achieves the best performance improving upon the baseline approaches that are trained exclusively on text features in FA-KES in about 20% inaccuracy, 15% in F1-measure, and 30% in AUC. It also achieves more robust probabilistic outcomes and higher top k precision and recall than the vanilla machine learning models.