Download this Paper Open PDF in Browser

Fake News in Social Networks

23 Pages Posted: 23 Aug 2017  

Christoph Aymanns

London School of Economics & Political Science (LSE) - London School of Economics

Jakob Foerster

University of Oxford

Co-Pierre Georg

Deutsche Bundesbank; University of Cape Town (UCT)

Date Written: August 21, 2017

Abstract

We model the spread of news as a social learning game on a network. Agents can either endorse or oppose a claim made in a piece of news, which itself may be either true or false. Agents base their decision on a private signal and their neighbors' past actions. Given these inputs, agents follow strategies derived via multi-agent deep reinforcement learning and receive utility from acting in accordance with the veracity of claims. Our framework yields strategies with agent utility close to a theoretical, Bayes optimal benchmark, while remaining flexible to model re-specification. Optimized strategies allow agents to correctly identify most false claims, when all agents receive unbiased private signals. However, an adversary's attempt to spread fake news by targeting a subset of agents with a biased private signal can be successful. Even more so when the adversary has information about agents' network position or private signal. When agents are aware of the presence of an adversary they re-optimize their strategies in the training stage and the adversary's attack is less effective. Hence, exposing agents to the possibility of fake news can be an effective way to curtail the spread of fake news in social networks. Our results also highlight that information about the users' private beliefs and their social network structure can be extremely valuable to adversaries and should be well protected.

Keywords: Social Learning, Networks, Multi-Agent Deep Reinforcement Learning

JEL Classification: D83, C45, D85

Suggested Citation

Aymanns, Christoph and Foerster, Jakob and Georg, Co-Pierre, Fake News in Social Networks (August 21, 2017). Available at SSRN: https://ssrn.com/abstract=3023320

Christoph Aymanns (Contact Author)

London School of Economics & Political Science (LSE) - London School of Economics ( email )

United Kingdom

Jakob Foerster

University of Oxford ( email )

Mansfield Road
Oxford, Oxfordshire OX1 4AU
United Kingdom

Co-Pierre Georg

Deutsche Bundesbank ( email )

Wilhelm-Epstein-Str. 14
Frankfurt/Main, 60431
Germany

University of Cape Town (UCT) ( email )

Private Bag X3
Rondebosch, 7701
South Africa

Paper statistics

Downloads
137
Rank
178,483
Abstract Views
622