Large Engagement Networks for Classifying Coordinated Campaigns and Organic Twitter Trends

2025-03-01

AI Summary

Distinguishing organic trends from coordinated inauthentic behavior (e.g., bot-driven campaigns) on social media remains challenging due to the absence of reliable ground-truth labels. Method: We propose a novel strategy for detecting coordinated attacks by identifying transient deletion patterns—abnormal, synchronized post removal—and introduce LEN, the first large-scale benchmark of social engagement networks comprising 179 coordinated campaigns and 135 organic trends. Our approach integrates social graph modeling, graph neural networks (GNNs), and anomaly detection, validated via rigorous human annotation. Contribution/Results: LEN provides fine-grained campaign-type annotations and enables, for the first time, large-scale graph classification for inauthentic trend detection. Experiments reveal that state-of-the-art GNNs exhibit significant performance limitations on this task, establishing LEN as a challenging new benchmark for both large-graph classification and misinformation detection.

Technology Category

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

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity
• Social Networks and Social Media: Fairness and bias in social network and social media analysis

Abstract

Social media users and inauthentic accounts, such as bots, may coordinate in promoting their topics. Such topics may give the impression that they are organically popular among the public, even though they are astroturfing campaigns that are centrally managed. It is challenging to predict if a topic is organic or a coordinated campaign due to the lack of reliable ground truth. In this paper, we create such ground truth by detecting the campaigns promoted by ephemeral astroturfing attacks. These attacks push any topic to Twitter's (X) trends list by employing bots that tweet in a coordinated manner in a short period and then immediately delete their tweets. We manually curate a dataset of organic Twitter trends. We then create engagement networks out of these datasets which can serve as a challenging testbed for graph classification task to distinguish between campaigns and organic trends. Engagement networks consist of users as nodes and engagements as edges (retweets, replies, and quotes) between users. We release the engagement networks for 179 campaigns and 135 non-campaigns, and also provide finer-grain labels to characterize the type of the campaigns and non-campaigns. Our dataset, LEN (Large Engagement Networks), is available in the URL below. In comparison to traditional graph classification datasets, which are small with tens of nodes and hundreds of edges at most, graphs in LEN are larger. The average graph in LEN has ~11K nodes and ~23K edges. We show that state-of-the-art GNN methods give only mediocre results for campaign vs. non-campaign and campaign type classification on LEN. LEN offers a unique and challenging playfield for the graph classification problem. We believe that LEN will help advance the frontiers of graph classification techniques on large networks and also provide an interesting use case in terms of distinguishing coordinated campaigns and organic trends.

Problem

• Detecting coordinated campaigns versus organic Twitter trends.
• Creating ground truth for distinguishing astroturfing attacks.
• Developing large engagement networks for graph classification tasks.

Innovation

• Detects ephemeral astroturfing attacks using engagement networks.
• Creates large-scale engagement networks for graph classification.
• Provides a dataset with 179 campaigns and 135 non-campaigns.