Fake News Mitigation via Point Process Based Intervention

TL;DR

This paper introduces a novel multistage intervention framework combining reinforcement learning and point process modeling to effectively mitigate fake news spread in social networks, demonstrated through real-time Twitter experiments.

Contribution

It presents the first multistage intervention approach integrating reinforcement learning with a multivariate Hawkes process for fake news mitigation.

Findings

Outperforms alternative methods on synthetic datasets.

Shows promising real-time mitigation performance on Twitter.

Optimizes intervention actions under budget constraints.

Abstract

We propose the first multistage intervention framework that tackles fake news in social networks by combining reinforcement learning with a point process network activity model. The spread of fake news and mitigation events within the network is modeled by a multivariate Hawkes process with additional exogenous control terms. By choosing a feature representation of states, defining mitigation actions and constructing reward functions to measure the effectiveness of mitigation activities, we map the problem of fake news mitigation into the reinforcement learning framework. We develop a policy iteration method unique to the multivariate networked point process, with the goal of optimizing the actions for maximal total reward under budget constraints. Our method shows promising performance in real-time intervention experiments on a Twitter network to mitigate a surrogate fake news campaign, and outperforms alternatives on synthetic datasets.