Distributed Rumor Blocking with Multiple Positive Cascades

TL;DR

This paper investigates how multiple independent agents generating positive cascades can effectively block rumors in social networks, analyzing the non-cooperative scenario and factors influencing rumor control.

Contribution

It introduces the P2P independent cascade model for multiple positive cascades and analyzes rumor blocking under non-cooperative agent behavior.

Findings

Nash equilibrium provides bounded rumor blocking effectiveness.

Cascade priority and activation order significantly influence rumor control.

Experimental results on real social networks validate the theoretical analysis.

Abstract

Misinformation and rumor can spread rapidly and widely through online social networks and therefore rumor controlling has become a critical issue. It is often assumed that there is a single authority whose goal is to minimize the spread of rumor by generating a positive cascade. In this paper, we study a more realistic scenario when there are multiple positive cascades generated by different agents. For the multiple-cascade diffusion, we propose the P2P independent cascade (PIC) model for private social communications. The main part of this paper is an analysis of the rumor blocking effect (i.e. the number of the users activated by rumor) when the agents non-cooperatively generate the positive cascades. We show that the rumor blocking effect provided by the Nash equilibrium will not be arbitrarily worse even if the positive cascades are generated non-cooperatively. In addition, we give a discussion on how the cascade priority and activation order affect the rumor blocking problem. We experimentally examine the Nash equilibrium of the proposed games by simulations done on real social network structures.