Identifying Cost-effective Debunkers for Multi-stage Fake News Mitigation Campaigns

TL;DR

This paper introduces a multi-stage, dynamic approach to selecting debunkers in social networks using reinforcement learning, significantly improving fake news mitigation effectiveness over existing static methods.

Contribution

It formulates the debunker selection as a reinforcement learning problem and proposes a greedy algorithm that predicts future states for optimal multi-stage mitigation.

Findings

Outperforms state-of-the-art baselines in mitigation effect

Effective in synthetic and real-world social networks

Demonstrates the benefit of dynamic, multi-stage selection over static methods

Abstract

Online social networks have become a fertile ground for spreading fake news. Methods to automatically mitigate fake news propagation have been proposed. Some studies focus on selecting top k influential users on social networks as debunkers, but the social influence of debunkers may not translate to wide mitigation information propagation as expected. Other studies assume a given set of debunkers and focus on optimizing intensity for debunkers to publish true news, but as debunkers are fixed, even if with high social influence and/or high intensity to post true news, the true news may not reach users exposed to fake news and therefore mitigation effect may be limited. In this paper, we propose the multi-stage fake news mitigation campaign where debunkers are dynamically selected within budget at each stage. We formulate it as a reinforcement learning problem and propose a greedy algorithm optimized by predicting future states so that the debunkers can be selected in a way that maximizes the overall mitigation effect. We conducted extensive experiments on synthetic and real-world social networks and show that our solution outperforms state-of-the-art baselines in terms of mitigation effect.