Density-aware Walks for Coordinated Campaign Detection

2025-06-16

AI Summary

Detecting covert coordinated manipulation on social platforms remains challenging. This paper addresses this problem by formulating fake trend detection as a graph classification task, using the large-scale Turkish election Twitter engagement network (LEN) dataset. We propose a novel Density-Aware Randomized Weighted Walk (RWW) method that, for the first time, incorporates local structural density metrics—such as k-core number and clique number—into the random walk transition mechanism and leverages Skip-gram to generate density-aware node embeddings. These embeddings are then integrated with a Message Passing Neural Network (MPNN) for end-to-end discriminative learning. Experiments on the LEN dataset demonstrate significant improvements: +11.8% in binary classification accuracy and +5.0% in multiclass accuracy. The results validate the effectiveness of jointly modeling density-aware structural encoding and MPNN-based graph representation learning, particularly for identifying large-scale, sparse coordinated attack graphs.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Coordinated campaigns frequently exploit social media platforms by artificially amplifying topics, making inauthentic trends appear organic, and misleading users into engagement. Distinguishing these coordinated efforts from genuine public discourse remains a significant challenge due to the sophisticated nature of such attacks. Our work focuses on detecting coordinated campaigns by modeling the problem as a graph classification task. We leverage the recently introduced Large Engagement Networks (LEN) dataset, which contains over 300 networks capturing engagement patterns from both fake and authentic trends on Twitter prior to the 2023 Turkish elections. The graphs in LEN were constructed by collecting interactions related to campaigns that stemmed from ephemeral astroturfing. Established graph neural networks (GNNs) struggle to accurately classify campaign graphs, highlighting the challenges posed by LEN due to the large size of its networks. To address this, we introduce a new graph classification method that leverages the density of local network structures. We propose a random weighted walk (RWW) approach in which node transitions are biased by local density measures such as degree, core number, or truss number. These RWWs are encoded using the Skip-gram model, producing density-aware structural embeddings for the nodes. Training message-passing neural networks (MPNNs) on these density-aware embeddings yields superior results compared to the simpler node features available in the dataset, with nearly a 12% and 5% improvement in accuracy for binary and multiclass classification, respectively. Our findings demonstrate that incorporating density-aware structural encoding with MPNNs provides a robust framework for identifying coordinated inauthentic behavior on social media networks such as Twitter.

Problem

• Detecting coordinated campaigns on social media platforms
• Improving graph classification for large engagement networks
• Enhancing accuracy in identifying inauthentic behavior

Innovation

• Graph classification using density-aware structural embeddings
• Random weighted walks biased by local density measures
• Message-passing neural networks for coordinated behavior detection