@inproceedings{sharma-etal-2022-disarm,
title = "{DISARM}: Detecting the Victims Targeted by Harmful Memes",
author = "Sharma, Shivam and
Akhtar, Md Shad and
Nakov, Preslav and
Chakraborty, Tanmoy",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2022",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-naacl.118",
doi = "10.18653/v1/2022.findings-naacl.118",
pages = "1572--1588",
abstract = "Internet memes have emerged as an increasingly popular means of communication on the web. Although memes are typically intended to elicit humour, they have been increasingly used to spread hatred, trolling, and cyberbullying, as well as to target specific individuals, communities, or society on political, socio-cultural, and psychological grounds. While previous work has focused on detecting harmful, hateful, and offensive memes in general, identifying whom these memes attack (i.e., the {`}victims{'}) remains a challenging and underexplored area. We attempt to address this problem in this paper. To this end, we create a dataset in which we annotate each meme with its victim(s) such as the name of the targeted person(s), organization(s), and community(ies). We then propose DISARM (Detecting vIctimS targeted by hARmful Memes), a framework that uses named-entity recognition and person identification to detect all entities a meme is referring to, and then, incorporates a novel contextualized multimodal deep neural network to classify whether the meme intends to harm these entities. We perform several systematic experiments on three different test sets, corresponding to entities that are (i) all seen while training, (ii) not seen as a harmful target while training, and (iii) not seen at all while training. The evaluation shows that DISARM significantly outperforms 10 unimodal and multimodal systems. Finally, we demonstrate that DISARM is interpretable and comparatively more generalizable and that it can reduce the relative error rate of harmful target identification by up to 9 {\%} absolute over multimodal baseline systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sharma-etal-2022-disarm">
<titleInfo>
<title>DISARM: Detecting the Victims Targeted by Harmful Memes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shivam</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Shad</namePart>
<namePart type="family">Akhtar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Internet memes have emerged as an increasingly popular means of communication on the web. Although memes are typically intended to elicit humour, they have been increasingly used to spread hatred, trolling, and cyberbullying, as well as to target specific individuals, communities, or society on political, socio-cultural, and psychological grounds. While previous work has focused on detecting harmful, hateful, and offensive memes in general, identifying whom these memes attack (i.e., the ‘victims’) remains a challenging and underexplored area. We attempt to address this problem in this paper. To this end, we create a dataset in which we annotate each meme with its victim(s) such as the name of the targeted person(s), organization(s), and community(ies). We then propose DISARM (Detecting vIctimS targeted by hARmful Memes), a framework that uses named-entity recognition and person identification to detect all entities a meme is referring to, and then, incorporates a novel contextualized multimodal deep neural network to classify whether the meme intends to harm these entities. We perform several systematic experiments on three different test sets, corresponding to entities that are (i) all seen while training, (ii) not seen as a harmful target while training, and (iii) not seen at all while training. The evaluation shows that DISARM significantly outperforms 10 unimodal and multimodal systems. Finally, we demonstrate that DISARM is interpretable and comparatively more generalizable and that it can reduce the relative error rate of harmful target identification by up to 9 % absolute over multimodal baseline systems.</abstract>
<identifier type="citekey">sharma-etal-2022-disarm</identifier>
<identifier type="doi">10.18653/v1/2022.findings-naacl.118</identifier>
<location>
<url>https://aclanthology.org/2022.findings-naacl.118</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>1572</start>
<end>1588</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DISARM: Detecting the Victims Targeted by Harmful Memes
%A Sharma, Shivam
%A Akhtar, Md Shad
%A Nakov, Preslav
%A Chakraborty, Tanmoy
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Findings of the Association for Computational Linguistics: NAACL 2022
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F sharma-etal-2022-disarm
%X Internet memes have emerged as an increasingly popular means of communication on the web. Although memes are typically intended to elicit humour, they have been increasingly used to spread hatred, trolling, and cyberbullying, as well as to target specific individuals, communities, or society on political, socio-cultural, and psychological grounds. While previous work has focused on detecting harmful, hateful, and offensive memes in general, identifying whom these memes attack (i.e., the ‘victims’) remains a challenging and underexplored area. We attempt to address this problem in this paper. To this end, we create a dataset in which we annotate each meme with its victim(s) such as the name of the targeted person(s), organization(s), and community(ies). We then propose DISARM (Detecting vIctimS targeted by hARmful Memes), a framework that uses named-entity recognition and person identification to detect all entities a meme is referring to, and then, incorporates a novel contextualized multimodal deep neural network to classify whether the meme intends to harm these entities. We perform several systematic experiments on three different test sets, corresponding to entities that are (i) all seen while training, (ii) not seen as a harmful target while training, and (iii) not seen at all while training. The evaluation shows that DISARM significantly outperforms 10 unimodal and multimodal systems. Finally, we demonstrate that DISARM is interpretable and comparatively more generalizable and that it can reduce the relative error rate of harmful target identification by up to 9 % absolute over multimodal baseline systems.
%R 10.18653/v1/2022.findings-naacl.118
%U https://aclanthology.org/2022.findings-naacl.118
%U https://doi.org/10.18653/v1/2022.findings-naacl.118
%P 1572-1588
Markdown (Informal)
[DISARM: Detecting the Victims Targeted by Harmful Memes](https://aclanthology.org/2022.findings-naacl.118) (Sharma et al., Findings 2022)
ACL
- Shivam Sharma, Md Shad Akhtar, Preslav Nakov, and Tanmoy Chakraborty. 2022. DISARM: Detecting the Victims Targeted by Harmful Memes. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 1572–1588, Seattle, United States. Association for Computational Linguistics.