@inproceedings{otiefy-etal-2020-woli,
title = "{WOLI} at {S}em{E}val-2020 Task 12: {A}rabic Offensive Language Identification on Different {T}witter Datasets",
author = "Otiefy, Yasser and
Abdelmalek, Ahmed and
El Hosary, Islam",
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-1.298",
doi = "10.18653/v1/2020.semeval-1.298",
pages = "2237--2243",
abstract = "Communicating through social platforms has become one of the principal means of personal communications and interactions. Unfortunately, healthy communication is often interfered by offensive language that can have damaging effects on the users. A key to fight offensive language on social media is the existence of an automatic offensive language detection system. This paper presents the results and the main findings of SemEval-2020, Task 12 OffensEval Sub-task A Zampieri et al. (2020), on Identifying and categorising Offensive Language in Social Media. The task was based on the Arabic OffensEval dataset Mubarak et al. (2020). In this paper, we describe the system submitted by WideBot AI Lab for the shared task which ranked 10th out of 52 participants with Macro-F1 86.9{\%} on the golden dataset under CodaLab username {``}yasserotiefy{''}. We experimented with various models and the best model is a linear SVM in which we use a combination of both character and word n-grams. We also introduced a neural network approach that enhanced the predictive ability of our system that includes CNN, highway network, Bi-LSTM, and attention layers.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="otiefy-etal-2020-woli">
<titleInfo>
<title>WOLI at SemEval-2020 Task 12: Arabic Offensive Language Identification on Different Twitter Datasets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yasser</namePart>
<namePart type="family">Otiefy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelmalek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Islam</namePart>
<namePart type="family">El Hosary</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>Communicating through social platforms has become one of the principal means of personal communications and interactions. Unfortunately, healthy communication is often interfered by offensive language that can have damaging effects on the users. A key to fight offensive language on social media is the existence of an automatic offensive language detection system. This paper presents the results and the main findings of SemEval-2020, Task 12 OffensEval Sub-task A Zampieri et al. (2020), on Identifying and categorising Offensive Language in Social Media. The task was based on the Arabic OffensEval dataset Mubarak et al. (2020). In this paper, we describe the system submitted by WideBot AI Lab for the shared task which ranked 10th out of 52 participants with Macro-F1 86.9% on the golden dataset under CodaLab username “yasserotiefy”. We experimented with various models and the best model is a linear SVM in which we use a combination of both character and word n-grams. We also introduced a neural network approach that enhanced the predictive ability of our system that includes CNN, highway network, Bi-LSTM, and attention layers.</abstract>
<identifier type="citekey">otiefy-etal-2020-woli</identifier>
<identifier type="doi">10.18653/v1/2020.semeval-1.298</identifier>
<location>
<url>https://aclanthology.org/2020.semeval-1.298</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>2237</start>
<end>2243</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WOLI at SemEval-2020 Task 12: Arabic Offensive Language Identification on Different Twitter Datasets
%A Otiefy, Yasser
%A Abdelmalek, Ahmed
%A El Hosary, Islam
%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 otiefy-etal-2020-woli
%X Communicating through social platforms has become one of the principal means of personal communications and interactions. Unfortunately, healthy communication is often interfered by offensive language that can have damaging effects on the users. A key to fight offensive language on social media is the existence of an automatic offensive language detection system. This paper presents the results and the main findings of SemEval-2020, Task 12 OffensEval Sub-task A Zampieri et al. (2020), on Identifying and categorising Offensive Language in Social Media. The task was based on the Arabic OffensEval dataset Mubarak et al. (2020). In this paper, we describe the system submitted by WideBot AI Lab for the shared task which ranked 10th out of 52 participants with Macro-F1 86.9% on the golden dataset under CodaLab username “yasserotiefy”. We experimented with various models and the best model is a linear SVM in which we use a combination of both character and word n-grams. We also introduced a neural network approach that enhanced the predictive ability of our system that includes CNN, highway network, Bi-LSTM, and attention layers.
%R 10.18653/v1/2020.semeval-1.298
%U https://aclanthology.org/2020.semeval-1.298
%U https://doi.org/10.18653/v1/2020.semeval-1.298
%P 2237-2243
Markdown (Informal)
[WOLI at SemEval-2020 Task 12: Arabic Offensive Language Identification on Different Twitter Datasets](https://aclanthology.org/2020.semeval-1.298) (Otiefy et al., SemEval 2020)
ACL