Anatomy of Elite and Mass Polarization in Social Networks

TL;DR

This work addresses the limitation of single-number polarization metrics by decomposing polarization into structural polarization and issue alignment, estimated separately for elites (core) and masses (periphery) using a two-group hierarchical framework. It combines a constrained planted-partition stochastic block model to identify polarized groups with a core-periphery approach to reveal hierarchies, and it introduces a decomposition of the polarization score $P_{AEI}$ into components for elites and masses, alongside separate $NMI$ measures for issue alignment in cores and peripheries. Applying the method to Finnish Twitter networks around the 2019 and 2023 elections, the study finds asymmetric group contributions, with elites consistently more aligned and a rising trend in mass issue alignment, demonstrating that polarization dynamics are not uniformly driven by all actors. The proposed hierarchical decomposition offers a nuanced view of polarization, revealing how elite cohesion, mass amplification, and cross-group interactions shape the observed polarization and how these processes evolve over time, with potential implications for understanding democratic discourse on online platforms.

Abstract

In the political arena of social platforms, opposing factions of varying sizes show asymmetrical patterns, and elites and masses within these groups have divergent motivations and influence,challenging simplistic views of polarization. Yet, existing methods for quantifying polarization reduce division to a single value, assuming uniform distribution of polarization online. While this approach can confirm the observed increase in political polarization in many societies, it overlooks complexities that could explain this phenomenon. Notably, opposing groups can have unequal impacts on polarization, and the literature shows division between elites and the masses is a critical factor to consider. We propose a method to decompose existing polarization measures in order to quantify the role of groups, determined by these distinct hierarchies, in the total polarization value. We applied this method to polarized topics in the Finnish Twittersphere surrounding the 2019 and 2023parliamentary elections. Our analysis reveals two key insights: 1) The impact of opposing groups on observed polarization is rarely balanced, and 2) while elites strongly contribute to structural polarization and consistently display greater alignment across various topics, the masses have also recently experienced a surge in issue alignment, a stronger form of polarization. Our findings suggest that the masses may not be as immune to an increasingly polarized environment as previously thought. This research provides a more nuanced understanding of polarization dynamics, offering potential insights into its underlying mechanisms and evolution

Figures (10)

• Figure 1: Our conceptualization enables categorizing the actions that lead to an increase in the structural polarization score. (A) is an example of a polarized network that has been partitioned into two groups representing communities with distinct stances on a specific political topic. Large nodes correspond to the elite members, while smaller ones indicate the mass. In (B), a new connection is formed between two elite members, making the elite group more cohesive. Another polarization increasing action is when a new connection is formed towards the elite group either from an existing node or a new node. This is depicted in (C) and the overall degree of this type of actions is called mass amplification. Lastly, a connection between two members belonging to the mass, is shown in (D), illustrating the interpretation of mass cohesion. Lower mass cohesion can be seen corresponding to higher centralized opinion leadership among the elites, as most connections are directed towards them.
• Figure 2: (A) demonstrates the increase in overall structural polarization across all networks, as measured by the AEI. Black bar corresponds to the proportion explained by the null model. The largest increase in the portion not explained by the null model was observed in the network representing economy-related discussions online. (B) The heatmaps depict the evolution of issue alignment over the four years, with 2019 on the left and 2023 on the right. Every pair of topics has experienced a substantial increase in the degree of alignment, as measured by the adjusted NMI. Climate and immigration were already reasonably aligned in 2019, however, the alignment doubled after four years. (C) illustrates the relationship between observed alignment and the average structural polarization scores for all topic pairs in both years—a slight linear relationship appears between the two quantities, possibly indicating that these phenomena are strenghtening each other. Note that in 2019, although some networks had high structural polarization scores, issue alignment remained relatively low. In contrast, by 2023, networks showed both high structural polarization and high issue alignment.
• Figure 3: (A) Polarization decomposition for structural contributions of different groups and their hierarchies to AEI-score. The figure illustrates the predominant influence of elite cohesion ($\widehat{i}_{{c}_{A}}$ & $\widehat{i}_{{c}_{B}}$), mass amplification ($\widehat{i}_{{cp}_{A}}$ & $\widehat{i}_{{cp}_{B}}$), and mass cohesion ($\widehat{i}_{{p}_{A}}$ & $\widehat{i}_{{p}_{B}}$) on the overall score. The green part of spectrum represents the impact of the bridge between the opposing entities ($2\times \widehat{e}_{AB}$). The contributions of different hierarchical members not only vary within individual networks but also across the distinct networks. The part of the spectrum that corresponds to the internal structures is shifted to the left by an amount equal to the cross-interactions. This enables us to read the unadjusted AEI score for each network directly from the figure. (B) Groups vary in their sizes, and mostly consists of the masses. Smaller groups can have a great impact on the observed polarization.
• Figure 4: (A) Elites are consistenly more aligned than masses across all topic pairs. Elites became more aligned in 2023, together with a smaller increase in the alignment of mass opinion on various issues. To capture the uncertainty around the observed values, we bootstrapped 500 pairs of networks for each topic pair. Each bootstrap sample represents a subgraph of the original network, where the sizes of cores and peripheries are subject to random fluctuations. We do this by sampling the nodes to groups according to their original group probabilities. (B) Elites tend to have higher marginal polarization as well compared to the mass. In both years, adding a new elite member to the economy network had the greatest impact. A weighted average of both groups' marginal values is applied to obtain a single value representing the hierarchy's mean effect on AEI.
• Figure 5: Activity patterns in the most polarized networks in 2023 separated at group and hierarchy level. In all networks, largest jump in activity takes place approximately three weeks before the election day, particularly within right-leaning group in immigration network. Which opposing group is more active depends on the issue. For instance, activity within the right-leaning elites is substantially higher in immigration and economy, whereas in climate, social security and education, left-leaning elites appear to be more active. The extent of activity of a specific group does not translate into the observed polarization. Figures for remaining topics and for 2019 can be found in Appendix \ref{['appendix-activity-patterns']}.