Evons: A Dataset for Fake and Real News Virality Analysis and Prediction

TL;DR

This paper introduces Evons, a new dataset of fake and real news articles with Facebook engagement metrics, images, and annotations, enabling analysis and prediction of news virality.

Contribution

The paper presents Evons, a comprehensive dataset with multimedia and engagement data, facilitating research on news virality and fake news detection.

Findings

Facebook engagement correlates with news virality.

Images and facial attributes provide additional predictive features.

Empirical analysis demonstrates the dataset's utility for virality prediction.

Abstract

We present a novel collection of news articles originating from fake and real news media sources for the analysis and prediction of news virality. Unlike existing fake news datasets which either contain claims or news article headline and body, in this collection each article is supported with a Facebook engagement count which we consider as an indicator of the article virality. In addition we also provide the article description and thumbnail image with which the article was shared on Facebook. These images were automatically annotated with object tags and color attributes. Using cloud based vision analysis tools, thumbnail images were also analyzed for faces and detected faces were annotated with facial attributes. We empirically investigate the use of this collection on an example task of article virality prediction.