Supervised Learning for Fake News Detection

TLDR

Recent research has focused on detecting fake news on social media by extracting features from news stories and their sources. The study aims to evaluate current fake‑news detection methods and introduce new features to improve automatic detection. The authors compare existing feature sets and their new features by measuring prediction performance on fake‑news detection tasks. The results show that certain features are particularly useful for detecting fake news and discuss practical applications, challenges, and opportunities.

Abstract

A large body of recent works has focused on understanding and detecting fake news stories that are disseminated on social media. To accomplish this goal, these works explore several types of features extracted from news stories, including source and posts from social media. In addition to exploring the main features proposed in the literature for fake news detection, we present a new set of features and measure the prediction performance of current approaches and features for automatic detection of fake news. Our results reveal interesting findings on the usefulness and importance of features for detecting false news. Finally, we discuss how fake news detection approaches can be used in the practice, highlighting challenges and opportunities.