@inproceedings{faye-etal-2024-exposing,
title = "Exposing propaganda: an analysis of stylistic cues comparing human annotations and machine classification",
author = "Faye, G{\'e}raud and
Icard, Benjamin and
Casanova, Morgane and
Chanson, Julien and
Maine, Fran{\c{c}}ois and
Bancilhon, Fran{\c{c}}ois and
Gadek, Guillaume and
Gravier, Guillaume and
{\'E}gr{\'e}, Paul",
editor = "Pyatkin, Valentina and
Fried, Daniel and
Stengel-Eskin, Elias and
Stengel-Eskin, Elias and
Liu, Alisa and
Pezzelle, Sandro",
booktitle = "Proceedings of the Third Workshop on Understanding Implicit and Underspecified Language",
month = mar,
year = "2024",
address = "Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.unimplicit-1.6",
pages = "62--72",
abstract = "This paper investigates the language of propaganda and its stylistic features. It presents the PPN dataset, standing for Propagandist Pseudo-News, a multisource, multilingual, multimodal dataset composed of news articles extracted from websites identified as propaganda sources by expert agencies. A limited sample from this set was randomly mixed with papers from the regular French press, and their URL masked, to conduct an annotation-experiment by humans, using 11 distinct labels. The results show that human annotators were able to reliably discriminate between the two types of press across each of the labels. We use different NLP techniques to identify the cues used by annotators, and to compare them with machine classification: first the analyzer VAGO to detect discourse vagueness and subjectivity, and then four different classifiers, two based on RoBERTa, one CATS using syntax, and one XGBoost combining syntactic and semantic features.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="faye-etal-2024-exposing">
<titleInfo>
<title>Exposing propaganda: an analysis of stylistic cues comparing human annotations and machine classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Géraud</namePart>
<namePart type="family">Faye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Icard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Morgane</namePart>
<namePart type="family">Casanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julien</namePart>
<namePart type="family">Chanson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">François</namePart>
<namePart type="family">Maine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">François</namePart>
<namePart type="family">Bancilhon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guillaume</namePart>
<namePart type="family">Gadek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guillaume</namePart>
<namePart type="family">Gravier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Égré</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Understanding Implicit and Underspecified Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Valentina</namePart>
<namePart type="family">Pyatkin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Fried</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elias</namePart>
<namePart type="family">Stengel-Eskin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alisa</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandro</namePart>
<namePart type="family">Pezzelle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper investigates the language of propaganda and its stylistic features. It presents the PPN dataset, standing for Propagandist Pseudo-News, a multisource, multilingual, multimodal dataset composed of news articles extracted from websites identified as propaganda sources by expert agencies. A limited sample from this set was randomly mixed with papers from the regular French press, and their URL masked, to conduct an annotation-experiment by humans, using 11 distinct labels. The results show that human annotators were able to reliably discriminate between the two types of press across each of the labels. We use different NLP techniques to identify the cues used by annotators, and to compare them with machine classification: first the analyzer VAGO to detect discourse vagueness and subjectivity, and then four different classifiers, two based on RoBERTa, one CATS using syntax, and one XGBoost combining syntactic and semantic features.</abstract>
<identifier type="citekey">faye-etal-2024-exposing</identifier>
<location>
<url>https://aclanthology.org/2024.unimplicit-1.6</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>62</start>
<end>72</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exposing propaganda: an analysis of stylistic cues comparing human annotations and machine classification
%A Faye, Géraud
%A Icard, Benjamin
%A Casanova, Morgane
%A Chanson, Julien
%A Maine, François
%A Bancilhon, François
%A Gadek, Guillaume
%A Gravier, Guillaume
%A Égré, Paul
%Y Pyatkin, Valentina
%Y Fried, Daniel
%Y Stengel-Eskin, Elias
%Y Liu, Alisa
%Y Pezzelle, Sandro
%S Proceedings of the Third Workshop on Understanding Implicit and Underspecified Language
%D 2024
%8 March
%I Association for Computational Linguistics
%C Malta
%F faye-etal-2024-exposing
%X This paper investigates the language of propaganda and its stylistic features. It presents the PPN dataset, standing for Propagandist Pseudo-News, a multisource, multilingual, multimodal dataset composed of news articles extracted from websites identified as propaganda sources by expert agencies. A limited sample from this set was randomly mixed with papers from the regular French press, and their URL masked, to conduct an annotation-experiment by humans, using 11 distinct labels. The results show that human annotators were able to reliably discriminate between the two types of press across each of the labels. We use different NLP techniques to identify the cues used by annotators, and to compare them with machine classification: first the analyzer VAGO to detect discourse vagueness and subjectivity, and then four different classifiers, two based on RoBERTa, one CATS using syntax, and one XGBoost combining syntactic and semantic features.
%U https://aclanthology.org/2024.unimplicit-1.6
%P 62-72
Markdown (Informal)
[Exposing propaganda: an analysis of stylistic cues comparing human annotations and machine classification](https://aclanthology.org/2024.unimplicit-1.6) (Faye et al., unimplicit-WS 2024)
ACL
- Géraud Faye, Benjamin Icard, Morgane Casanova, Julien Chanson, François Maine, François Bancilhon, Guillaume Gadek, Guillaume Gravier, and Paul Égré. 2024. Exposing propaganda: an analysis of stylistic cues comparing human annotations and machine classification. In Proceedings of the Third Workshop on Understanding Implicit and Underspecified Language, pages 62–72, Malta. Association for Computational Linguistics.