@inproceedings{antypas-etal-2021-covid,
title = "{COVID}-19 and Misinformation: A Large-Scale Lexical Analysis on {T}witter",
author = "Antypas, Dimosthenis and
Camacho-Collados, Jose and
Preece, Alun and
Rogers, David",
editor = "Kabbara, Jad and
Lin, Haitao and
Paullada, Amandalynne and
Vamvas, Jannis",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Student Research Workshop",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-srw.13",
doi = "10.18653/v1/2021.acl-srw.13",
pages = "119--126",
abstract = "Social media is often used by individuals and organisations as a platform to spread misinformation. With the recent coronavirus pandemic we have seen a surge of misinformation on Twitter, posing a danger to public health. In this paper, we compile a large COVID-19 Twitter misinformation corpus and perform an analysis to discover patterns with respect to vocabulary usage. Among others, our analysis reveals that the variety of topics and vocabulary usage are considerably more limited and negative in tweets related to misinformation than in randomly extracted tweets. In addition to our qualitative analysis, our experimental results show that a simple linear model based only on lexical features is effective in identifying misinformation-related tweets (with accuracy over 80{\%}), providing evidence to the fact that the vocabulary used in misinformation largely differs from generic tweets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="antypas-etal-2021-covid">
<titleInfo>
<title>COVID-19 and Misinformation: A Large-Scale Lexical Analysis on Twitter</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dimosthenis</namePart>
<namePart type="family">Antypas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="family">Camacho-Collados</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alun</namePart>
<namePart type="family">Preece</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Student Research Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jad</namePart>
<namePart type="family">Kabbara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haitao</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amandalynne</namePart>
<namePart type="family">Paullada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jannis</namePart>
<namePart type="family">Vamvas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Social media is often used by individuals and organisations as a platform to spread misinformation. With the recent coronavirus pandemic we have seen a surge of misinformation on Twitter, posing a danger to public health. In this paper, we compile a large COVID-19 Twitter misinformation corpus and perform an analysis to discover patterns with respect to vocabulary usage. Among others, our analysis reveals that the variety of topics and vocabulary usage are considerably more limited and negative in tweets related to misinformation than in randomly extracted tweets. In addition to our qualitative analysis, our experimental results show that a simple linear model based only on lexical features is effective in identifying misinformation-related tweets (with accuracy over 80%), providing evidence to the fact that the vocabulary used in misinformation largely differs from generic tweets.</abstract>
<identifier type="citekey">antypas-etal-2021-covid</identifier>
<identifier type="doi">10.18653/v1/2021.acl-srw.13</identifier>
<location>
<url>https://aclanthology.org/2021.acl-srw.13</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>119</start>
<end>126</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T COVID-19 and Misinformation: A Large-Scale Lexical Analysis on Twitter
%A Antypas, Dimosthenis
%A Camacho-Collados, Jose
%A Preece, Alun
%A Rogers, David
%Y Kabbara, Jad
%Y Lin, Haitao
%Y Paullada, Amandalynne
%Y Vamvas, Jannis
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Student Research Workshop
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F antypas-etal-2021-covid
%X Social media is often used by individuals and organisations as a platform to spread misinformation. With the recent coronavirus pandemic we have seen a surge of misinformation on Twitter, posing a danger to public health. In this paper, we compile a large COVID-19 Twitter misinformation corpus and perform an analysis to discover patterns with respect to vocabulary usage. Among others, our analysis reveals that the variety of topics and vocabulary usage are considerably more limited and negative in tweets related to misinformation than in randomly extracted tweets. In addition to our qualitative analysis, our experimental results show that a simple linear model based only on lexical features is effective in identifying misinformation-related tweets (with accuracy over 80%), providing evidence to the fact that the vocabulary used in misinformation largely differs from generic tweets.
%R 10.18653/v1/2021.acl-srw.13
%U https://aclanthology.org/2021.acl-srw.13
%U https://doi.org/10.18653/v1/2021.acl-srw.13
%P 119-126
Markdown (Informal)
[COVID-19 and Misinformation: A Large-Scale Lexical Analysis on Twitter](https://aclanthology.org/2021.acl-srw.13) (Antypas et al., ACL-IJCNLP 2021)
ACL
- Dimosthenis Antypas, Jose Camacho-Collados, Alun Preece, and David Rogers. 2021. COVID-19 and Misinformation: A Large-Scale Lexical Analysis on Twitter. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Student Research Workshop, pages 119–126, Online. Association for Computational Linguistics.