Voter model can accurately predict individual opinions in online populations

TL;DR

This paper demonstrates that the multi-state voter model with zealots can accurately predict individual opinions and identify like-minded users in online populations, validated using Twitter data from the 2017 French elections.

Contribution

It provides empirical evidence that the voter model effectively captures individual opinions and social connections in online environments, a novel validation at the user level.

Findings

Strong correlation between model predictions and user political leanings

Discord probabilities identify like-minded user pairs accurately

Supports validity of voter models in complex online settings

Abstract

Models of opinion dynamics describe how opinions are shaped in various environments. While these models are able to replicate general opinion distributions observed in real-world scenarios, their capacity to align with data at the user level remains mostly untested. We evaluate the capacity of the multi-state voter model with zealots to capture individual opinions in a fine-grained Twitter dataset collected during the 2017 French Presidential elections. Our findings reveal a strong correspondence between individual opinion distributions in the equilibrium state of the model and ground-truth political leanings of the users. Additionally, we demonstrate that discord probabilities accurately identify pairs of like-minded users. These results emphasize the validity of the voter model in complex settings, and advocate for further empirical evaluations of opinion dynamics models at the user level.