Network-informed Prompt Engineering against Organized Astroturf Campaigns under Extreme Class Imbalance

2025-01-21

AI Summary

Detecting coordinated political astroturfing campaigns on social platforms under extreme class imbalance—where opposing groups differ drastically in size and labeled data is scarce—remains a critical challenge. Method: We propose a zero-training, zero-fine-tuning LLM-driven approach that (i) incorporates user interaction network structure into prompt engineering via a network-aware prompting framework, and (ii) introduces Balanced Retrieval-Augmented Generation (RAG) to mitigate class-imbalance bias in zero-shot inference. Contribution/Results: Our method requires no manual annotation, data augmentation, or model fine-tuning, departing from conventional joint graph neural network–NLP modeling paradigms. Evaluated on real-world X (Twitter) data, it achieves 2–3× improvements in precision, recall, and F1-score over graph-based baselines, significantly enhancing detection sensitivity for small-scale coordinated astroturfing activities.

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: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Detecting organized political campaigns is of paramount importance in fighting against disinformation on social media. Existing approaches for the identification of such organized actions employ techniques mostly from network science, graph machine learning and natural language processing. Their ultimate goal is to analyze the relationships and interactions (e.g. re-posting) among users and the textual similarities of their posts. Despite their effectiveness in recognizing astroturf campaigns, these methods face significant challenges, notably the class imbalance in available training datasets. To mitigate this issue, recent methods usually resort to data augmentation or increasing the number of positive samples, which may not always be feasible or sufficient in real-world settings. Following a different path, in this paper, we propose a novel framework for identifying astroturf campaigns based solely on large language models (LLMs), introducing a Balanced Retrieval-Augmented Generation (Balanced RAG) component. Our approach first gives both textual information concerning the posts (in our case tweets) and the user interactions of the social network as input to a language model. Then, through prompt engineering and the proposed Balanced RAG method, it effectively detects coordinated disinformation campaigns on X (Twitter). The proposed framework does not require any training or fine-tuning of the language model. Instead, by strategically harnessing the strengths of prompt engineering and Balanced RAG, it facilitates LLMs to overcome the effects of class imbalance and effectively identify coordinated political campaigns. The experimental results demonstrate that by incorporating the proposed prompt engineering and Balanced RAG methods, our framework outperforms the traditional graph-based baselines, achieving 2x-3x improvements in terms of precision, recall and F1 scores.

Problem

• Social Media
• Political Astroturfing
• Imbalanced Data

Innovation

• Large Language Models
• Balanced Retrieval
• Enhanced Detection Accuracy