Modeling change in public sentiment with nonlocal reaction-diffusion equations

Abstract

This is a brief "proof of concept" article that shows nonlocal diffusion is well suited to the study of pattern formation and the particular application of public sentiment. We use a nonlocal reaction-diffusion equation to model the evolution of public sentiment in a population that interacts with other individuals. We employ a pseudo-random convolution kernel as a symmetric matrix of lognormally distributed values. This kernel models the influence of individuals when interacting with others. Change in sentiment emerges and may converge to a polarized state. Other more complicated states occur whereby a mixed polarization emerges.