Parameter Evaluation of a Simple Mean-Field Model of Social Interaction

TL;DR

This paper develops a statistical mechanics model of social interaction, introducing a mean-field approach to quantify peer imitation and phase transition phenomena in social systems.

Contribution

It presents a novel mean-field model for social interaction, along with a parameter estimation method validated on diverse datasets, linking social psychology and phase transition theory.

Findings

Estimated interaction parameters are positive, confirming peer imitation behavior.

Parameters are within the phase transition regime, indicating critical social dynamics.

Model successfully fits data from different social contexts.

Abstract

The aim of this work is to implement a statistical mechanics theory of social interaction, generalizing econometric discrete choice models. A class of simple mean field discrete models is introduced and discussed both from the theoretical and phenomenological point of view. We propose a parameter evaluation procedure and test it by fitting our model against three families of data coming from different cases: the estimated interaction parameters are found to have similar positive values establishing a quantitative confirmation of the peer imitation behavior found in social psychology. Moreover all the values of the interaction parameters belong to the phase transition regime suggesting its possible role in the study of social systems.