@inproceedings{bhattacharya-etal-2020-developing,
title = "Developing a Multilingual Annotated Corpus of Misogyny and Aggression",
author = "Bhattacharya, Shiladitya and
Singh, Siddharth and
Kumar, Ritesh and
Bansal, Akanksha and
Bhagat, Akash and
Dawer, Yogesh and
Lahiri, Bornini and
Ojha, Atul Kr.",
editor = "Kumar, Ritesh and
Ojha, Atul Kr. and
Lahiri, Bornini and
Zampieri, Marcos and
Malmasi, Shervin and
Murdock, Vanessa and
Kadar, Daniel",
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-1.25/",
pages = "158--168",
language = "eng",
ISBN = "979-10-95546-56-6",
abstract = "In this paper, we discuss the development of a multilingual annotated corpus of misogyny and aggression in Indian English, Hindi, and Indian Bangla as part of a project on studying and automatically identifying misogyny and communalism on social media (the ComMA Project). The dataset is collected from comments on YouTube videos and currently contains a total of over 20,000 comments. The comments are annotated at two levels - aggression (overtly aggressive, covertly aggressive, and non-aggressive) and misogyny (gendered and non-gendered). We describe the process of data collection, the tagset used for annotation, and issues and challenges faced during the process of annotation. Finally, we discuss the results of the baseline experiments conducted to develop a classifier for misogyny in the three languages."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhattacharya-etal-2020-developing">
<titleInfo>
<title>Developing a Multilingual Annotated Corpus of Misogyny and Aggression</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shiladitya</namePart>
<namePart type="family">Bhattacharya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siddharth</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akanksha</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akash</namePart>
<namePart type="family">Bhagat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yogesh</namePart>
<namePart type="family">Dawer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bornini</namePart>
<namePart type="family">Lahiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Trolling, Aggression and Cyberbullying</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bornini</namePart>
<namePart type="family">Lahiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shervin</namePart>
<namePart type="family">Malmasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vanessa</namePart>
<namePart type="family">Murdock</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Kadar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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>In this paper, we discuss the development of a multilingual annotated corpus of misogyny and aggression in Indian English, Hindi, and Indian Bangla as part of a project on studying and automatically identifying misogyny and communalism on social media (the ComMA Project). The dataset is collected from comments on YouTube videos and currently contains a total of over 20,000 comments. The comments are annotated at two levels - aggression (overtly aggressive, covertly aggressive, and non-aggressive) and misogyny (gendered and non-gendered). We describe the process of data collection, the tagset used for annotation, and issues and challenges faced during the process of annotation. Finally, we discuss the results of the baseline experiments conducted to develop a classifier for misogyny in the three languages.</abstract>
<identifier type="citekey">bhattacharya-etal-2020-developing</identifier>
<location>
<url>https://aclanthology.org/2020.trac-1.25/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>158</start>
<end>168</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Developing a Multilingual Annotated Corpus of Misogyny and Aggression
%A Bhattacharya, Shiladitya
%A Singh, Siddharth
%A Kumar, Ritesh
%A Bansal, Akanksha
%A Bhagat, Akash
%A Dawer, Yogesh
%A Lahiri, Bornini
%A Ojha, Atul Kr.
%Y Kumar, Ritesh
%Y Ojha, Atul Kr.
%Y Lahiri, Bornini
%Y Zampieri, Marcos
%Y Malmasi, Shervin
%Y Murdock, Vanessa
%Y Kadar, Daniel
%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 eng
%F bhattacharya-etal-2020-developing
%X In this paper, we discuss the development of a multilingual annotated corpus of misogyny and aggression in Indian English, Hindi, and Indian Bangla as part of a project on studying and automatically identifying misogyny and communalism on social media (the ComMA Project). The dataset is collected from comments on YouTube videos and currently contains a total of over 20,000 comments. The comments are annotated at two levels - aggression (overtly aggressive, covertly aggressive, and non-aggressive) and misogyny (gendered and non-gendered). We describe the process of data collection, the tagset used for annotation, and issues and challenges faced during the process of annotation. Finally, we discuss the results of the baseline experiments conducted to develop a classifier for misogyny in the three languages.
%U https://aclanthology.org/2020.trac-1.25/
%P 158-168
Markdown (Informal)
[Developing a Multilingual Annotated Corpus of Misogyny and Aggression](https://aclanthology.org/2020.trac-1.25/) (Bhattacharya et al., TRAC 2020)
ACL
- Shiladitya Bhattacharya, Siddharth Singh, Ritesh Kumar, Akanksha Bansal, Akash Bhagat, Yogesh Dawer, Bornini Lahiri, and Atul Kr. Ojha. 2020. Developing a Multilingual Annotated Corpus of Misogyny and Aggression. In Proceedings of the Second Workshop on Trolling, Aggression and Cyberbullying, pages 158–168, Marseille, France. European Language Resources Association (ELRA).