Bayesian updating as basis for opinion dynamics models

Opinion Dynamics tries to model how different opinions spread in a society. At this point, the existing models lack a common theoretical basis. In this article, I propose to use a decision-theoretic framework, based on the updating of subjective probabilities, as that basis. We will see we get a basic tool for a better understanding of the interaction between the agents in Opinion Dynamics problems and for creating new models. I will review the few existing applications of Bayesian update rules to both discrete and continuous opinion problems, and show that several traditional models can be obtained as special cases or approximations from these Bayesian models. The empirical basis and useful properties of the framework will be discussed, and examples of how the framework can be used to describe different problems given.