Predictive Linguistic Cues for Fake News: A Societal AI Problem

(Journal Publication)

Access paper here

Abstract: Media news is making a large part of public opinion and, therefore, must not be fake. News on websites, blogs, and social media must be analyzed before publication. In this paper, we present linguistic characteristics of media news items to differentiate between fake and real news using machine learning algorithms. Neural fake news generation, headlines created by machines, semantic incongruities in text, and image captions generated by machines are other types of fake news problems. These problems use neural networks which mainly control distributional features rather than evidence. We propose applying correlation between the features set and class and correlation among the features to compute correlation attribute evaluation metric and covariance metric to compute the variance of attributes over the news items. Features such as unique, negative, positive, and cardinal numbers with high values on the metrics are observed to provide a high area under the curve (AUC) and F1-score.