@inproceedings{koufakou-scott-2020-lexicon,
title = "Lexicon-Enhancement of Embedding-based Approaches Towards the Detection of Abusive Language",
author = "Koufakou, Anna and
Scott, Jason",
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-1.24",
pages = "150--157",
abstract = "Detecting abusive language is a significant research topic, which has received a lot of attention recently. Our work focuses on detecting personal attacks in online conversations. As previous research on this task has largely used deep learning based on embeddings, we explore the use of lexicons to enhance embedding-based methods in an effort to see how these methods apply in the particular task of detecting personal attacks. The methods implemented and experimented with in this paper are quite different from each other, not only in the type of lexicons they use (sentiment or semantic), but also in the way they use the knowledge from the lexicons, in order to construct or to change embeddings that are ultimately fed into the learning model. The sentiment lexicon approaches focus on integrating sentiment information (in the form of sentiment embeddings) into the learning model. The semantic lexicon approaches focus on transforming the original word embeddings so that they better represent relationships extracted from a semantic lexicon. Based on our experimental results, semantic lexicon methods are superior to the rest of the methods in this paper, with at least 4{\%} macro-averaged F1 improvement over the baseline.",
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="koufakou-scott-2020-lexicon">
<titleInfo>
<title>Lexicon-Enhancement of Embedding-based Approaches Towards the Detection of Abusive Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Koufakou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</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>
<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>Detecting abusive language is a significant research topic, which has received a lot of attention recently. Our work focuses on detecting personal attacks in online conversations. As previous research on this task has largely used deep learning based on embeddings, we explore the use of lexicons to enhance embedding-based methods in an effort to see how these methods apply in the particular task of detecting personal attacks. The methods implemented and experimented with in this paper are quite different from each other, not only in the type of lexicons they use (sentiment or semantic), but also in the way they use the knowledge from the lexicons, in order to construct or to change embeddings that are ultimately fed into the learning model. The sentiment lexicon approaches focus on integrating sentiment information (in the form of sentiment embeddings) into the learning model. The semantic lexicon approaches focus on transforming the original word embeddings so that they better represent relationships extracted from a semantic lexicon. Based on our experimental results, semantic lexicon methods are superior to the rest of the methods in this paper, with at least 4% macro-averaged F1 improvement over the baseline.</abstract>
<identifier type="citekey">koufakou-scott-2020-lexicon</identifier>
<location>
<url>https://aclanthology.org/2020.trac-1.24</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>150</start>
<end>157</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lexicon-Enhancement of Embedding-based Approaches Towards the Detection of Abusive Language
%A Koufakou, Anna
%A Scott, Jason
%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 English
%F koufakou-scott-2020-lexicon
%X Detecting abusive language is a significant research topic, which has received a lot of attention recently. Our work focuses on detecting personal attacks in online conversations. As previous research on this task has largely used deep learning based on embeddings, we explore the use of lexicons to enhance embedding-based methods in an effort to see how these methods apply in the particular task of detecting personal attacks. The methods implemented and experimented with in this paper are quite different from each other, not only in the type of lexicons they use (sentiment or semantic), but also in the way they use the knowledge from the lexicons, in order to construct or to change embeddings that are ultimately fed into the learning model. The sentiment lexicon approaches focus on integrating sentiment information (in the form of sentiment embeddings) into the learning model. The semantic lexicon approaches focus on transforming the original word embeddings so that they better represent relationships extracted from a semantic lexicon. Based on our experimental results, semantic lexicon methods are superior to the rest of the methods in this paper, with at least 4% macro-averaged F1 improvement over the baseline.
%U https://aclanthology.org/2020.trac-1.24
%P 150-157
Markdown (Informal)
[Lexicon-Enhancement of Embedding-based Approaches Towards the Detection of Abusive Language](https://aclanthology.org/2020.trac-1.24) (Koufakou & Scott, TRAC 2020)
ACL