Post-hoc evaluation of nodes influence in information cascades: the case of coordinated accounts

TL;DR

This paper formalizes a post-hoc framework to assess the influence of coordinated accounts in information cascades by modeling cascades as directed trees with binary node labels. It develops two placement strategies—an unconstrained optimal algorithm and a greedy fixed-k approach—and analyzes both synthetic trees and real Twitter cascades from the 2019 UK election. The findings show coordinated accounts exert substantially less influence than the optimal or greedy strategies would allow, driven by limited resources and suboptimal placement, with real placements resembling random labeling. The work suggests Coordinated Inauthentic Behavior may have a smaller effect on information diffusion than commonly assumed, while highlighting methodological limitations and avenues for broader application in future studies.

Abstract

In the last years, social media has gained an unprecedented amount of attention, playing a pivotal role in shaping the contemporary landscape of communication and connection. However, Coordinated Inhautentic Behaviour (CIB), defined as orchestrated efforts by entities to deceive or mislead users about their identity and intentions, has emerged as a tactic to exploit the online discourse. In this study, we quantify the efficacy of CIB tactics by defining a general framework for evaluating the influence of a subset of nodes in a directed tree. We design two algorithms that provide optimal and greedy post-hoc placement strategies that lead to maximising the configuration influence. We then consider cascades from information spreading on Twitter to compare the observed behaviour with our algorithms. The results show that, according to our model, coordinated accounts are quite inefficient in terms of their network influence, thus suggesting that they may play a less pivotal role than expected. Moreover, the causes of these poor results may be found in two separate aspects: a bad placement strategy and a scarcity of resources.

Figures (2)

• Figure 1: Example of an optimal configuration. The coordinated accounts are highlighted in red.
• Figure 2: $(a)$ The configuration that maximizes $I^* (n)$ and minimizes $k^* (n)$. $(b)$ The configuration that minimizes $I^* (n)$ and maximizes $k^* (n)$.

Theorems & Definitions (1)

• Theorem 1