@inproceedings{424b380450b64f9ba046dd3714640899,
title = "Clustering Document Parts: Detecting and Characterizing Influence Campaigns from Documents",
abstract = "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.",
author = "Zhengxiang Wang and Owen Rambow",
note = "Publisher Copyright: {\textcopyright} 2024 Association for Computational Linguistics.; 6thWorkshop on Natural Language Processing and Computational Social Science, NLP+CSS 2024 ; Conference date: 21-06-2024",
year = "2024",
language = "English",
series = "NLP+CSS 2024 - 6thWorkshop on Natural Language Processing and Computational Social Science, Proceedings of the Workshop",
publisher = "Association for Computational Linguistics (ACL)",
pages = "132--143",
editor = "Dallas Card and Anjalie Field and Dirk Hovy and Katherine Keith",
booktitle = "NLP+CSS 2024 - 6thWorkshop on Natural Language Processing and Computational Social Science, Proceedings of the Workshop",
}