@inproceedings{mompelat-etal-2022-loco,
title = "How {``}Loco{''} Is the {LOCO} Corpus? Annotating the Language of Conspiracy Theories",
author = {Mompelat, Ludovic and
Tian, Zuoyu and
Kessler, Amanda and
Luettgen, Matthew and
Rajanala, Aaryana and
K{\"u}bler, Sandra and
Seelig, Michelle},
editor = "Pradhan, Sameer and
Kuebler, Sandra",
booktitle = "Proceedings of the 16th Linguistic Annotation Workshop (LAW-XVI) within LREC2022",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.law-1.14",
pages = "111--119",
abstract = "Conspiracy theories have found a new channel on the internet and spread by bringing together like-minded people, thus functioning as an echo chamber. The new 88-million word corpus \textit{Language of Conspiracy} (LOCO) was created with the intention to provide a text collection to study how the language of conspiracy differs from mainstream language. We use this corpus to develop a robust annotation scheme that will allow us to distinguish between documents containing conspiracy language and documents that do not contain any conspiracy content or that propagate conspiracy theories via misinformation (which we explicitly disregard in our work). We find that focusing on indicators of a belief in a conspiracy combined with textual cues of conspiracy language allows us to reach a substantial agreement (based on Fleiss{'} kappa and Krippendorff{'}s alpha). We also find that the automatic retrieval methods used to collect the corpus work well in finding mainstream documents, but include some documents in the conspiracy category that would not belong there based on our definition.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mompelat-etal-2022-loco">
<titleInfo>
<title>How “Loco” Is the LOCO Corpus? Annotating the Language of Conspiracy Theories</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ludovic</namePart>
<namePart type="family">Mompelat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zuoyu</namePart>
<namePart type="family">Tian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amanda</namePart>
<namePart type="family">Kessler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Luettgen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaryana</namePart>
<namePart type="family">Rajanala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandra</namePart>
<namePart type="family">Kübler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michelle</namePart>
<namePart type="family">Seelig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Linguistic Annotation Workshop (LAW-XVI) within LREC2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sameer</namePart>
<namePart type="family">Pradhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandra</namePart>
<namePart type="family">Kuebler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Conspiracy theories have found a new channel on the internet and spread by bringing together like-minded people, thus functioning as an echo chamber. The new 88-million word corpus Language of Conspiracy (LOCO) was created with the intention to provide a text collection to study how the language of conspiracy differs from mainstream language. We use this corpus to develop a robust annotation scheme that will allow us to distinguish between documents containing conspiracy language and documents that do not contain any conspiracy content or that propagate conspiracy theories via misinformation (which we explicitly disregard in our work). We find that focusing on indicators of a belief in a conspiracy combined with textual cues of conspiracy language allows us to reach a substantial agreement (based on Fleiss’ kappa and Krippendorff’s alpha). We also find that the automatic retrieval methods used to collect the corpus work well in finding mainstream documents, but include some documents in the conspiracy category that would not belong there based on our definition.</abstract>
<identifier type="citekey">mompelat-etal-2022-loco</identifier>
<location>
<url>https://aclanthology.org/2022.law-1.14</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>111</start>
<end>119</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How “Loco” Is the LOCO Corpus? Annotating the Language of Conspiracy Theories
%A Mompelat, Ludovic
%A Tian, Zuoyu
%A Kessler, Amanda
%A Luettgen, Matthew
%A Rajanala, Aaryana
%A Kübler, Sandra
%A Seelig, Michelle
%Y Pradhan, Sameer
%Y Kuebler, Sandra
%S Proceedings of the 16th Linguistic Annotation Workshop (LAW-XVI) within LREC2022
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F mompelat-etal-2022-loco
%X Conspiracy theories have found a new channel on the internet and spread by bringing together like-minded people, thus functioning as an echo chamber. The new 88-million word corpus Language of Conspiracy (LOCO) was created with the intention to provide a text collection to study how the language of conspiracy differs from mainstream language. We use this corpus to develop a robust annotation scheme that will allow us to distinguish between documents containing conspiracy language and documents that do not contain any conspiracy content or that propagate conspiracy theories via misinformation (which we explicitly disregard in our work). We find that focusing on indicators of a belief in a conspiracy combined with textual cues of conspiracy language allows us to reach a substantial agreement (based on Fleiss’ kappa and Krippendorff’s alpha). We also find that the automatic retrieval methods used to collect the corpus work well in finding mainstream documents, but include some documents in the conspiracy category that would not belong there based on our definition.
%U https://aclanthology.org/2022.law-1.14
%P 111-119
Markdown (Informal)
[How “Loco” Is the LOCO Corpus? Annotating the Language of Conspiracy Theories](https://aclanthology.org/2022.law-1.14) (Mompelat et al., LAW 2022)
ACL