@inproceedings{wang-rambow-2024-clustering,
title = "Clustering Document Parts: Detecting and Characterizing Influence Campaigns from Documents",
author = "Wang, Zhengxiang and
Rambow, Owen",
editor = "Card, Dallas and
Field, Anjalie and
Hovy, Dirk and
Keith, Katherine",
booktitle = "Proceedings of the Sixth Workshop on Natural Language Processing and Computational Social Science (NLP+CSS 2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.nlpcss-1.10",
doi = "10.18653/v1/2024.nlpcss-1.10",
pages = "132--143",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-rambow-2024-clustering">
<titleInfo>
<title>Clustering Document Parts: Detecting and Characterizing Influence Campaigns from Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhengxiang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Workshop on Natural Language Processing and Computational Social Science (NLP+CSS 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dallas</namePart>
<namePart type="family">Card</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anjalie</namePart>
<namePart type="family">Field</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dirk</namePart>
<namePart type="family">Hovy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katherine</namePart>
<namePart type="family">Keith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">wang-rambow-2024-clustering</identifier>
<identifier type="doi">10.18653/v1/2024.nlpcss-1.10</identifier>
<location>
<url>https://aclanthology.org/2024.nlpcss-1.10</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>132</start>
<end>143</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Clustering Document Parts: Detecting and Characterizing Influence Campaigns from Documents
%A Wang, Zhengxiang
%A Rambow, Owen
%Y Card, Dallas
%Y Field, Anjalie
%Y Hovy, Dirk
%Y Keith, Katherine
%S Proceedings of the Sixth Workshop on Natural Language Processing and Computational Social Science (NLP+CSS 2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F wang-rambow-2024-clustering
%X 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.
%R 10.18653/v1/2024.nlpcss-1.10
%U https://aclanthology.org/2024.nlpcss-1.10
%U https://doi.org/10.18653/v1/2024.nlpcss-1.10
%P 132-143
Markdown (Informal)
[Clustering Document Parts: Detecting and Characterizing Influence Campaigns from Documents](https://aclanthology.org/2024.nlpcss-1.10) (Wang & Rambow, NLP+CSS-WS 2024)
ACL