@inproceedings{suryawanshi-etal-2020-multimodal,
title = "Multimodal Meme Dataset ({M}ulti{OFF}) for Identifying Offensive Content in Image and Text",
author = "Suryawanshi, Shardul and
Chakravarthi, Bharathi Raja and
Arcan, Mihael and
Buitelaar, Paul",
booktitle = "Proceedings of the Second Workshop on Trolling, Aggression and Cyberbullying",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/2020.trac-1.6",
pages = "32--41",
abstract = "A meme is a form of media that spreads an idea or emotion across the internet. As posting meme has become a new form of communication of the web, due to the multimodal nature of memes, postings of hateful memes or related events like trolling, cyberbullying are increasing day by day. Hate speech, offensive content and aggression content detection have been extensively explored in a single modality such as text or image. However, combining two modalities to detect offensive content is still a developing area. Memes make it even more challenging since they express humour and sarcasm in an implicit way, because of which the meme may not be offensive if we only consider the text or the image. Therefore, it is necessary to combine both modalities to identify whether a given meme is offensive or not. Since there was no publicly available dataset for multimodal offensive meme content detection, we leveraged the memes related to the 2016 U.S. presidential election and created the MultiOFF multimodal meme dataset for offensive content detection dataset. We subsequently developed a classifier for this task using the MultiOFF dataset. We use an early fusion technique to combine the image and text modality and compare it with a text- and an image-only baseline to investigate its effectiveness. Our results show improvements in terms of Precision, Recall, and F-Score. The code and dataset for this paper is published in \textit{ \url{https://github.com/bharathichezhiyan/Multimodal-Meme-Classification-Identifying-Offensive-Content-in-Image-and-Text} }",
language = "English",
ISBN = "979-10-95546-56-6",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="suryawanshi-etal-2020-multimodal">
<titleInfo>
<title>Multimodal Meme Dataset (MultiOFF) for Identifying Offensive Content in Image and Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shardul</namePart>
<namePart type="family">Suryawanshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">Raja</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mihael</namePart>
<namePart type="family">Arcan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Buitelaar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Trolling, Aggression and Cyberbullying</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-56-6</identifier>
</relatedItem>
<abstract>A meme is a form of media that spreads an idea or emotion across the internet. As posting meme has become a new form of communication of the web, due to the multimodal nature of memes, postings of hateful memes or related events like trolling, cyberbullying are increasing day by day. Hate speech, offensive content and aggression content detection have been extensively explored in a single modality such as text or image. However, combining two modalities to detect offensive content is still a developing area. Memes make it even more challenging since they express humour and sarcasm in an implicit way, because of which the meme may not be offensive if we only consider the text or the image. Therefore, it is necessary to combine both modalities to identify whether a given meme is offensive or not. Since there was no publicly available dataset for multimodal offensive meme content detection, we leveraged the memes related to the 2016 U.S. presidential election and created the MultiOFF multimodal meme dataset for offensive content detection dataset. We subsequently developed a classifier for this task using the MultiOFF dataset. We use an early fusion technique to combine the image and text modality and compare it with a text- and an image-only baseline to investigate its effectiveness. Our results show improvements in terms of Precision, Recall, and F-Score. The code and dataset for this paper is published in https://github.com/bharathichezhiyan/Multimodal-Meme-Classification-Identifying-Offensive-Content-in-Image-and-Text </abstract>
<identifier type="citekey">suryawanshi-etal-2020-multimodal</identifier>
<location>
<url>https://aclanthology.org/2020.trac-1.6</url>
</location>
<part>
<date>2020-may</date>
<extent unit="page">
<start>32</start>
<end>41</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multimodal Meme Dataset (MultiOFF) for Identifying Offensive Content in Image and Text
%A Suryawanshi, Shardul
%A Chakravarthi, Bharathi Raja
%A Arcan, Mihael
%A Buitelaar, Paul
%S Proceedings of the Second Workshop on Trolling, Aggression and Cyberbullying
%D 2020
%8 may
%I European Language Resources Association (ELRA)
%C Marseille, France
%@ 979-10-95546-56-6
%G English
%F suryawanshi-etal-2020-multimodal
%X A meme is a form of media that spreads an idea or emotion across the internet. As posting meme has become a new form of communication of the web, due to the multimodal nature of memes, postings of hateful memes or related events like trolling, cyberbullying are increasing day by day. Hate speech, offensive content and aggression content detection have been extensively explored in a single modality such as text or image. However, combining two modalities to detect offensive content is still a developing area. Memes make it even more challenging since they express humour and sarcasm in an implicit way, because of which the meme may not be offensive if we only consider the text or the image. Therefore, it is necessary to combine both modalities to identify whether a given meme is offensive or not. Since there was no publicly available dataset for multimodal offensive meme content detection, we leveraged the memes related to the 2016 U.S. presidential election and created the MultiOFF multimodal meme dataset for offensive content detection dataset. We subsequently developed a classifier for this task using the MultiOFF dataset. We use an early fusion technique to combine the image and text modality and compare it with a text- and an image-only baseline to investigate its effectiveness. Our results show improvements in terms of Precision, Recall, and F-Score. The code and dataset for this paper is published in https://github.com/bharathichezhiyan/Multimodal-Meme-Classification-Identifying-Offensive-Content-in-Image-and-Text
%U https://aclanthology.org/2020.trac-1.6
%P 32-41
Markdown (Informal)
[Multimodal Meme Dataset (MultiOFF) for Identifying Offensive Content in Image and Text](https://aclanthology.org/2020.trac-1.6) (Suryawanshi et al., TRAC 2020)
ACL