We introduce the Ising Network Opinion Formation (INOF) model and apply it to the analysis of networks from six different Wikipedia language editions. In this model, Ising spins represent opinions and are placed at network nodes/articles. The steady-state polarization of these opinions is determined through Monte Carlo iterations, where the orientation of a given spin is influenced by the in-going links from other spins. The seed nodes of confrontation maintain a fixed spin/opinion, while all other nodes evolve toward their steady-state opinions during the iterative process.

We analyze several cases of opinion confrontation. For example, in the competition between Socialism-Communism and Capitalism-Imperialism, we observe that the global network opinion leans toward the former in all six Wikipedia editions. Additionally, the model identifies opinion preferences for different countries and political leaders, showing strong agreement with intuitive expectations. We also explore opinion dynamics between Christianity and Islam, as well as between the Democratic and Republican parties in the USA.

Moreover, we analyze the convergence, dynamics, and equilibrium properties of this nonlinear model, examining how these aspects evolve over time. The INOF model demonstrates significant potential for a wide range of applications in the study of directed complex networks.