FacTweet: Profiling Fake News Twitter Accounts

TL;DR

This paper introduces FacTweet, a neural recurrent model that detects fake news Twitter accounts by analyzing account timelines as sequences, capturing stylistic signatures for improved accuracy over traditional methods.

Contribution

The paper proposes a novel sequential modeling approach that considers entire account timelines and stylistic features, advancing fake news detection at the account level.

Findings

Sequential modeling outperforms baseline methods

Stylistic features improve detection accuracy

Account-level analysis enhances fake news identification

Abstract

We present an approach to detect fake news in Twitter at the account level using a neural recurrent model and a variety of different semantic and stylistic features. Our method extracts a set of features from the timelines of news Twitter accounts by reading their posts as chunks, rather than dealing with each tweet independently. We show the experimental benefits of modeling latent stylistic signatures of mixed fake and real news with a sequential model over a wide range of strong baselines.