# Clustering Document Parts: Detecting and Characterizing Influence Campaigns from Documents

arXiv: https://arxiv.org/abs/2402.17151 · HTML: https://mlsanity.com/paper/2402.17151/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 32 references that are in the map.
- First posted on arXiv 27 Feb 2024.

## Builds on (most cited first, 9 of 9)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [BotOrNot: A System to Evaluate Social Bots](https://mlsanity.com/paper/1602.00975/) (2016)
- [Analyzing the Digital Traces of Political Manipulation: The 2016 Russian Interference Twitter Campaign](https://mlsanity.com/paper/1802.04291/) (2018)
- [Disinformation and Social Bot Operations in the Run Up to the 2017 French Presidential Election](https://mlsanity.com/paper/1707.00086/) (2017)
- [Leveraging Large Language Models to Detect Influence Campaigns in Social Media](https://mlsanity.com/paper/2311.07816/) (2023)
- [FACTOID: A New Dataset for Identifying Misinformation Spreaders and Political Bias](https://mlsanity.com/paper/2205.06181/) (2022)
- [Bots, Disinformation, and the First Trump Impeachment](https://mlsanity.com/paper/2204.08915/) (2022)
- [Detecting Influence Campaigns in Social Networks Using the Ising Model](https://mlsanity.com/paper/1805.10244/) (2018)

## Abstract (arXiv)

We propose a novel clustering pipeline to detect and characterize influence campaigns from documents. This approach clusters parts of document, detects clusters that likely reflect an influence campaign, and then identifies documents linked to an influence campaign via their association with the high-influence clusters. Our approach outperforms both the direct document-level classification and the direct document-level clustering approach in predicting if a document is part of an influence campaign. We propose various novel techniques to enhance our pipeline, including using an existing event factuality prediction system to obtain document parts, and aggregating multiple clustering experiments to improve the performance of both cluster and document classification. Classifying documents after clustering not only accurately extracts the parts of the documents that are relevant to influence campaigns, but also captures influence campaigns as a coordinated and holistic phenomenon. Our approach makes possible more fine-grained and interpretable characterizations of influence campaigns from documents.