Supermajority Sentiment Detection with External Influence in Large Social Networks

TL;DR

This paper studies how accurately one can detect the overall sentiment in large social networks, considering the effects of network structure, user biases, and external influences, using an Ising model framework.

Contribution

It introduces a comprehensive analysis of supermajority sentiment detection incorporating external influence within an Ising Markov random field model.

Findings

Detection accuracy depends on network structure and parameters.

External influence level significantly impacts sentiment detection.

The model provides insights into asymptotic detection performance.

Abstract

In a large social network whose members harbor binary sentiments towards an issue, we investigate the asymptotic accuracy of sentiment detection. We model the user sentiments by an Ising Markov random field model and allow the user sentiments to be biased by an external influence. We consider a general supermajority sentiment detection problem and show that the detection accuracy is affected by the network structure, its parameters, as well as the external influence level.