A Generalisation of Voter Model: Influential Nodes and Convergence Properties

TL;DR

This paper introduces a generalized voter model accounting for varying influence, neutral opinions, and reluctance to change, providing new insights into influence maximization and convergence behavior in social networks.

Contribution

It proposes a novel generalized voter model, proves NP-hardness of influence maximization, offers an optimal approximation algorithm, and analyzes convergence properties including exponential and polynomial bounds.

Findings

The influence maximization problem is NP-hard.

The proposed algorithm outperforms existing methods in experiments.

Convergence can be exponential in general but polynomial in strongly connected graphs.

Abstract

Consider an undirected graph G, representing a social network, where each node is blue or red, corresponding to positive or negative opinion on a topic. In the voter model, in discrete time rounds, each node picks a neighbour uniformly at random and adopts its colour. Despite its significant popularity, this model does not capture some fundamental real-world characteristics such as the difference in the strengths of individuals connections, individuals with neutral opinion on a topic, and individuals who are reluctant to update their opinion. To address these issues, we introduce and study a generalisation of the voter model. Motivating by campaigning strategies, we study the problem of selecting a set of seeds blue nodes to maximise the expected number of blue nodes after some rounds. We prove that the problem is NP- hard and provide a polynomial time approximation algorithm with the best possible approximation guarantee. Our experiments on real-world and synthetic graph data demonstrate that the proposed algorithm outperforms other algorithms. We also investigate the convergence properties of the model. We prove that the process could take an exponential number of rounds to converge. However, if we limit ourselves to strongly connected graphs, the convergence time is polynomial and the period (the number of states in convergence) divides the length of all cycles in the graph.