@inproceedings{sharifirad-matwin-2019-using,
title = "Using Attention-based Bidirectional {LSTM} to Identify Different Categories of Offensive Language Directed Toward Female Celebrities",
author = "Sharifirad, Sima and
Matwin, Stan",
editor = "Axelrod, Amittai and
Yang, Diyi and
Cunha, Rossana and
Shaikh, Samira and
Waseem, Zeerak",
booktitle = "Proceedings of the 2019 Workshop on Widening NLP",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-3616/",
pages = "46--48",
abstract = "Social media posts reflect the emotions, intentions and mental state of the users. Twitter users who harass famous female figures may do so with different intentions and intensities. Recent studies have published datasets focusing on different types of online harassment, vulgar language, and emotional intensities. We trained, validate and test our proposed model, attention-based bidirectional neural network, on the three datasets:{\textquotedblright}online harassment{\textquotedblright}, {\textquotedblleft}vulgar language{\textquotedblright} and {\textquotedblleft}valance{\textquotedblright} and achieved state of the art performance in two of the datasets. We report F1 score for each dataset separately along with the final precision, recall and macro-averaged F1 score. In addition, we identify ten female figures from different professions and racial backgrounds who have experienced harassment on Twitter. We tested the trained models on ten collected corpuses each related to one famous female figure to predict the type of harassing language, the type of vulgar language and the degree of intensity of language occurring on their social platforms. Interestingly, the achieved results show different patterns of linguistic use targeting different racial background and occupations. The contribution of this study is two-fold. From the technical perspective, our proposed methodology is shown to be effective with a good margin in comparison to the previous state-of-the-art results on one of the two available datasets. From the social perspective, we introduce a methodology which can unlock facts about the nature of offensive language targeting women on online social platforms. The collected dataset will be shared publicly for further investigation."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sharifirad-matwin-2019-using">
<titleInfo>
<title>Using Attention-based Bidirectional LSTM to Identify Different Categories of Offensive Language Directed Toward Female Celebrities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sima</namePart>
<namePart type="family">Sharifirad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stan</namePart>
<namePart type="family">Matwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Workshop on Widening NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amittai</namePart>
<namePart type="family">Axelrod</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diyi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rossana</namePart>
<namePart type="family">Cunha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samira</namePart>
<namePart type="family">Shaikh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeerak</namePart>
<namePart type="family">Waseem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Social media posts reflect the emotions, intentions and mental state of the users. Twitter users who harass famous female figures may do so with different intentions and intensities. Recent studies have published datasets focusing on different types of online harassment, vulgar language, and emotional intensities. We trained, validate and test our proposed model, attention-based bidirectional neural network, on the three datasets:”online harassment”, “vulgar language” and “valance” and achieved state of the art performance in two of the datasets. We report F1 score for each dataset separately along with the final precision, recall and macro-averaged F1 score. In addition, we identify ten female figures from different professions and racial backgrounds who have experienced harassment on Twitter. We tested the trained models on ten collected corpuses each related to one famous female figure to predict the type of harassing language, the type of vulgar language and the degree of intensity of language occurring on their social platforms. Interestingly, the achieved results show different patterns of linguistic use targeting different racial background and occupations. The contribution of this study is two-fold. From the technical perspective, our proposed methodology is shown to be effective with a good margin in comparison to the previous state-of-the-art results on one of the two available datasets. From the social perspective, we introduce a methodology which can unlock facts about the nature of offensive language targeting women on online social platforms. The collected dataset will be shared publicly for further investigation.</abstract>
<identifier type="citekey">sharifirad-matwin-2019-using</identifier>
<location>
<url>https://aclanthology.org/W19-3616/</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>46</start>
<end>48</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using Attention-based Bidirectional LSTM to Identify Different Categories of Offensive Language Directed Toward Female Celebrities
%A Sharifirad, Sima
%A Matwin, Stan
%Y Axelrod, Amittai
%Y Yang, Diyi
%Y Cunha, Rossana
%Y Shaikh, Samira
%Y Waseem, Zeerak
%S Proceedings of the 2019 Workshop on Widening NLP
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F sharifirad-matwin-2019-using
%X Social media posts reflect the emotions, intentions and mental state of the users. Twitter users who harass famous female figures may do so with different intentions and intensities. Recent studies have published datasets focusing on different types of online harassment, vulgar language, and emotional intensities. We trained, validate and test our proposed model, attention-based bidirectional neural network, on the three datasets:”online harassment”, “vulgar language” and “valance” and achieved state of the art performance in two of the datasets. We report F1 score for each dataset separately along with the final precision, recall and macro-averaged F1 score. In addition, we identify ten female figures from different professions and racial backgrounds who have experienced harassment on Twitter. We tested the trained models on ten collected corpuses each related to one famous female figure to predict the type of harassing language, the type of vulgar language and the degree of intensity of language occurring on their social platforms. Interestingly, the achieved results show different patterns of linguistic use targeting different racial background and occupations. The contribution of this study is two-fold. From the technical perspective, our proposed methodology is shown to be effective with a good margin in comparison to the previous state-of-the-art results on one of the two available datasets. From the social perspective, we introduce a methodology which can unlock facts about the nature of offensive language targeting women on online social platforms. The collected dataset will be shared publicly for further investigation.
%U https://aclanthology.org/W19-3616/
%P 46-48
Markdown (Informal)
[Using Attention-based Bidirectional LSTM to Identify Different Categories of Offensive Language Directed Toward Female Celebrities](https://aclanthology.org/W19-3616/) (Sharifirad & Matwin, WiNLP 2019)
ACL