Fake news propagate differently from real news even at early stages of spreading

TL;DR

This study analyzes how fake news spreads differently from real news on social media platforms like Weibo and Twitter, revealing early-stage structural signals that could aid in fake news detection.

Contribution

It provides empirical evidence of distinct early propagation patterns of fake versus real news and highlights the potential of topological features for early detection.

Findings

Fake news spreads differently from real news within five hours of initial reposts.

Structural signals in propagation networks can distinguish fake news early.

Early topological features offer new avenues for fake news detection.

Abstract

Social media can be a double-edged sword for society, either as a convenient channel exchanging ideas or as an unexpected conduit circulating fake news through a large population. While existing studies of fake news focus on theoretical modeling of propagation or identification methods based on machine learning, it is important to understand the realistic mechanisms between theoretical models and black-box methods. Here we track large databases of fake news and real news in both, Weibo in China and Twitter in Japan from different culture, which include their complete traces of re-postings. We find in both online social networks that fake news spreads distinctively from real news even at early stages of propagation, e.g. five hours after the first re-postings. Our finding demonstrates collective structural signals that help to understand the different propagation evolution of fake news and real news. Different from earlier studies, identifying the topological properties of the information propagation at early stages may offer novel features for early detection of fake news in social media.