@inproceedings{ferreira-cruz-etal-2019-sentence,
title = "On Sentence Representations for Propaganda Detection: From Handcrafted Features to Word Embeddings",
author = "Ferreira Cruz, Andr{\'e} and
Rocha, Gil and
Lopes Cardoso, Henrique",
editor = "Feldman, Anna and
Da San Martino, Giovanni and
Barr{\'o}n-Cede{\~n}o, Alberto and
Brew, Chris and
Leberknight, Chris and
Nakov, Preslav",
booktitle = "Proceedings of the Second Workshop on Natural Language Processing for Internet Freedom: Censorship, Disinformation, and Propaganda",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-5015",
doi = "10.18653/v1/D19-5015",
pages = "107--112",
abstract = "Bias is ubiquitous in most online sources of natural language, from news media to social networks. Given the steady shift in news consumption behavior from traditional outlets to online sources, the automatic detection of propaganda, in which information is shaped to purposefully foster a predetermined agenda, is an increasingly crucial task. To this goal, we explore the task of sentence-level propaganda detection, and experiment with both handcrafted features and learned dense semantic representations. We also experiment with random undersampling of the majority class (non-propaganda) to curb the influence of class distribution on the system{'}s performance, leading to marked improvements on the minority class (propaganda). Our best performing system uses pre-trained ELMo word embeddings, followed by a bidirectional LSTM and an attention layer. We have submitted a 5-model ensemble of our best performing system to the NLP4IF shared task on sentence-level propaganda detection (team LIACC), achieving rank 10 among 25 participants, with 59.5 F1-score.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ferreira-cruz-etal-2019-sentence">
<titleInfo>
<title>On Sentence Representations for Propaganda Detection: From Handcrafted Features to Word Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="family">Ferreira Cruz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gil</namePart>
<namePart type="family">Rocha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henrique</namePart>
<namePart type="family">Lopes Cardoso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Natural Language Processing for Internet Freedom: Censorship, Disinformation, and Propaganda</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Feldman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Barrón-Cedeño</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Brew</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Leberknight</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Bias is ubiquitous in most online sources of natural language, from news media to social networks. Given the steady shift in news consumption behavior from traditional outlets to online sources, the automatic detection of propaganda, in which information is shaped to purposefully foster a predetermined agenda, is an increasingly crucial task. To this goal, we explore the task of sentence-level propaganda detection, and experiment with both handcrafted features and learned dense semantic representations. We also experiment with random undersampling of the majority class (non-propaganda) to curb the influence of class distribution on the system’s performance, leading to marked improvements on the minority class (propaganda). Our best performing system uses pre-trained ELMo word embeddings, followed by a bidirectional LSTM and an attention layer. We have submitted a 5-model ensemble of our best performing system to the NLP4IF shared task on sentence-level propaganda detection (team LIACC), achieving rank 10 among 25 participants, with 59.5 F1-score.</abstract>
<identifier type="citekey">ferreira-cruz-etal-2019-sentence</identifier>
<identifier type="doi">10.18653/v1/D19-5015</identifier>
<location>
<url>https://aclanthology.org/D19-5015</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>107</start>
<end>112</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On Sentence Representations for Propaganda Detection: From Handcrafted Features to Word Embeddings
%A Ferreira Cruz, André
%A Rocha, Gil
%A Lopes Cardoso, Henrique
%Y Feldman, Anna
%Y Da San Martino, Giovanni
%Y Barrón-Cedeño, Alberto
%Y Brew, Chris
%Y Leberknight, Chris
%Y Nakov, Preslav
%S Proceedings of the Second Workshop on Natural Language Processing for Internet Freedom: Censorship, Disinformation, and Propaganda
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F ferreira-cruz-etal-2019-sentence
%X Bias is ubiquitous in most online sources of natural language, from news media to social networks. Given the steady shift in news consumption behavior from traditional outlets to online sources, the automatic detection of propaganda, in which information is shaped to purposefully foster a predetermined agenda, is an increasingly crucial task. To this goal, we explore the task of sentence-level propaganda detection, and experiment with both handcrafted features and learned dense semantic representations. We also experiment with random undersampling of the majority class (non-propaganda) to curb the influence of class distribution on the system’s performance, leading to marked improvements on the minority class (propaganda). Our best performing system uses pre-trained ELMo word embeddings, followed by a bidirectional LSTM and an attention layer. We have submitted a 5-model ensemble of our best performing system to the NLP4IF shared task on sentence-level propaganda detection (team LIACC), achieving rank 10 among 25 participants, with 59.5 F1-score.
%R 10.18653/v1/D19-5015
%U https://aclanthology.org/D19-5015
%U https://doi.org/10.18653/v1/D19-5015
%P 107-112
Markdown (Informal)
[On Sentence Representations for Propaganda Detection: From Handcrafted Features to Word Embeddings](https://aclanthology.org/D19-5015) (Ferreira Cruz et al., NLP4IF 2019)
ACL