The Rise and Fall of Fake News sites: A Traffic Analysis

TL;DR

This paper investigates the operational behavior of fake news websites through traffic analysis, revealing their lifespan, synchronization, content sharing, third-party support, and user traffic, and develops a machine learning classifier for detection.

Contribution

It provides the first comprehensive analysis of fake news website behavior and introduces a content-agnostic ML classifier for automatic detection beyond blacklists.

Findings

Fake news sites tend to have specific lifespan patterns.

They often synchronize their activity periods.

A machine learning classifier achieves high accuracy in detection.

Abstract

Over the past decade, we have witnessed the rise of misinformation on the Internet, with online users constantly falling victims of fake news. A multitude of past studies have analyzed fake news diffusion mechanics and detection and mitigation techniques. However, there are still open questions about their operational behavior such as: How old are fake news websites? Do they typically stay online for long periods of time? Do such websites synchronize with each other their up and down time? Do they share similar content through time? Which third-parties support their operations? How much user traffic do they attract, in comparison to mainstream or real news websites? In this paper, we perform a first of its kind investigation to answer such questions regarding the online presence of fake news websites and characterize their behavior in comparison to real news websites. Based on our findings, we build a content-agnostic ML classifier for automatic detection of fake news websites (i.e. accuracy) that are not yet included in manually curated blacklists.