Limiting the Spread of Fake News on Social Media Platforms by Evaluating Users' Trustworthiness

TL;DR

This paper proposes a trustworthiness estimation mechanism for social media users to limit fake news spread, using a Bayesian approach based on fact-checker reviews, achieving high accuracy with minimal performance impact.

Contribution

It introduces a content-independent fake news mitigation method leveraging user trustworthiness estimation through Bayesian analysis, implemented as a social media plugin.

Findings

Over 99% of fake news identified with no false positives.

High estimation accuracy with only a few thousand user exposures.

Minimal performance overhead on social media platform operations.

Abstract

Today's social media platforms enable to spread both authentic and fake news very quickly. Some approaches have been proposed to automatically detect such "fake" news based on their content, but it is difficult to agree on universal criteria of authenticity (which can be bypassed by adversaries once known). Besides, it is obviously impossible to have each news item checked by a human. In this paper, we a mechanism to limit the spread of fake news which is not based on content. It can be implemented as a plugin on a social media platform. The principle is as follows: a team of fact-checkers reviews a small number of news items (the most popular ones), which enables to have an estimation of each user's inclination to share fake news items. Then, using a Bayesian approach, we estimate the trustworthiness of future news items, and treat accordingly those of them that pass a certain "untrustworthiness" threshold. We then evaluate the effectiveness and overhead of this technique on a large Twitter graph. We show that having a few thousands users exposed to one given news item enables to reach a very precise estimation of its reliability. We thus identify more than 99% of fake news items with no false positives. The performance impact is very small: the induced overhead on the 90th percentile latency is less than 3%, and less than 8% on the throughput of user operations.