@inproceedings{paul-etal-2020-cybertronics,
title = "{C}yber{T}ronics at {S}em{E}val-2020 Task 12: Multilingual Offensive Language Identification over Social Media",
author = "Paul, Sayanta and
Saha, Sriparna and
Hasanuzzaman, Mohammed",
editor = "Herbelot, Aurelie and
Zhu, Xiaodan and
Palmer, Alexis and
Schneider, Nathan and
May, Jonathan and
Shutova, Ekaterina",
booktitle = "Proceedings of the Fourteenth Workshop on Semantic Evaluation",
month = dec,
year = "2020",
address = "Barcelona (online)",
publisher = "International Committee for Computational Linguistics",
url = "https://aclanthology.org/2020.semeval-1.253",
doi = "10.18653/v1/2020.semeval-1.253",
pages = "1925--1931",
abstract = "The SemEval-2020 Task 12 (OffensEval) challenge focuses on detection of signs of offensiveness using posts or comments over social media. This task has been organized for several languages, e.g., Arabic, Danish, English, Greek and Turkish. It has featured three related sub-tasks for English language: sub-task A was to discriminate between offensive and non-offensive posts, the focus of sub-task B was on the type of offensive content in the post and finally, in sub-task C, proposed systems had to identify the target of the offensive posts. The corpus for each of the languages is developed using the posts and comments over Twitter, a popular social media platform. We have participated in this challenge and submitted results for different languages. The current work presents different machine learning and deep learning techniques and analyzes their performance for offensiveness prediction which involves various classifiers and feature engineering schemes. The experimental analysis on the training set shows that SVM using language specific pre-trained word embedding (Fasttext) outperforms the other methods. Our system achieves a macro-averaged F1 score of 0.45 for Arabic language, 0.43 for Greek language and 0.54 for Turkish language.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="paul-etal-2020-cybertronics">
<titleInfo>
<title>CyberTronics at SemEval-2020 Task 12: Multilingual Offensive Language Identification over Social Media</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sayanta</namePart>
<namePart type="family">Paul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sriparna</namePart>
<namePart type="family">Saha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="family">Hasanuzzaman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourteenth Workshop on Semantic Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aurelie</namePart>
<namePart type="family">Herbelot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodan</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">May</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona (online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The SemEval-2020 Task 12 (OffensEval) challenge focuses on detection of signs of offensiveness using posts or comments over social media. This task has been organized for several languages, e.g., Arabic, Danish, English, Greek and Turkish. It has featured three related sub-tasks for English language: sub-task A was to discriminate between offensive and non-offensive posts, the focus of sub-task B was on the type of offensive content in the post and finally, in sub-task C, proposed systems had to identify the target of the offensive posts. The corpus for each of the languages is developed using the posts and comments over Twitter, a popular social media platform. We have participated in this challenge and submitted results for different languages. The current work presents different machine learning and deep learning techniques and analyzes their performance for offensiveness prediction which involves various classifiers and feature engineering schemes. The experimental analysis on the training set shows that SVM using language specific pre-trained word embedding (Fasttext) outperforms the other methods. Our system achieves a macro-averaged F1 score of 0.45 for Arabic language, 0.43 for Greek language and 0.54 for Turkish language.</abstract>
<identifier type="citekey">paul-etal-2020-cybertronics</identifier>
<identifier type="doi">10.18653/v1/2020.semeval-1.253</identifier>
<location>
<url>https://aclanthology.org/2020.semeval-1.253</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>1925</start>
<end>1931</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CyberTronics at SemEval-2020 Task 12: Multilingual Offensive Language Identification over Social Media
%A Paul, Sayanta
%A Saha, Sriparna
%A Hasanuzzaman, Mohammed
%Y Herbelot, Aurelie
%Y Zhu, Xiaodan
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y May, Jonathan
%Y Shutova, Ekaterina
%S Proceedings of the Fourteenth Workshop on Semantic Evaluation
%D 2020
%8 December
%I International Committee for Computational Linguistics
%C Barcelona (online)
%F paul-etal-2020-cybertronics
%X The SemEval-2020 Task 12 (OffensEval) challenge focuses on detection of signs of offensiveness using posts or comments over social media. This task has been organized for several languages, e.g., Arabic, Danish, English, Greek and Turkish. It has featured three related sub-tasks for English language: sub-task A was to discriminate between offensive and non-offensive posts, the focus of sub-task B was on the type of offensive content in the post and finally, in sub-task C, proposed systems had to identify the target of the offensive posts. The corpus for each of the languages is developed using the posts and comments over Twitter, a popular social media platform. We have participated in this challenge and submitted results for different languages. The current work presents different machine learning and deep learning techniques and analyzes their performance for offensiveness prediction which involves various classifiers and feature engineering schemes. The experimental analysis on the training set shows that SVM using language specific pre-trained word embedding (Fasttext) outperforms the other methods. Our system achieves a macro-averaged F1 score of 0.45 for Arabic language, 0.43 for Greek language and 0.54 for Turkish language.
%R 10.18653/v1/2020.semeval-1.253
%U https://aclanthology.org/2020.semeval-1.253
%U https://doi.org/10.18653/v1/2020.semeval-1.253
%P 1925-1931
Markdown (Informal)
[CyberTronics at SemEval-2020 Task 12: Multilingual Offensive Language Identification over Social Media](https://aclanthology.org/2020.semeval-1.253) (Paul et al., SemEval 2020)
ACL
