@inproceedings{almatarneh-etal-2019-citius,
title = "{C}i{TIUS}-{COLE} at {S}em{E}val-2019 Task 5: Combining Linguistic Features to Identify Hate Speech Against Immigrants and Women on Multilingual Tweets",
author = "Almatarneh, Sattam and
Gamallo, Pablo and
Pena, Francisco J. Ribadas",
editor = "May, Jonathan and
Shutova, Ekaterina and
Herbelot, Aurelie and
Zhu, Xiaodan and
Apidianaki, Marianna and
Mohammad, Saif M.",
booktitle = "Proceedings of the 13th International Workshop on Semantic Evaluation",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/S19-2068/",
doi = "10.18653/v1/S19-2068",
pages = "387--390",
abstract = "This article describes the strategy submitted by the CiTIUS-COLE team to SemEval 2019 Task 5, a task which consists of binary classi- fication where the system predicting whether a tweet in English or in Spanish is hateful against women or immigrants or not. The proposed strategy relies on combining linguis- tic features to improve the classifier{'}s perfor- mance. More precisely, the method combines textual and lexical features, embedding words with the bag of words in Term Frequency- Inverse Document Frequency (TF-IDF) repre- sentation. The system performance reaches about 81{\%} F1 when it is applied to the training dataset, but its F1 drops to 36{\%} on the official test dataset for the English and 64{\%} for the Spanish language concerning the hate speech class"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="almatarneh-etal-2019-citius">
<titleInfo>
<title>CiTIUS-COLE at SemEval-2019 Task 5: Combining Linguistic Features to Identify Hate Speech Against Immigrants and Women on Multilingual Tweets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sattam</namePart>
<namePart type="family">Almatarneh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pablo</namePart>
<namePart type="family">Gamallo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francisco</namePart>
<namePart type="given">J</namePart>
<namePart type="given">Ribadas</namePart>
<namePart type="family">Pena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 13th International Workshop on Semantic Evaluation</title>
</titleInfo>
<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>
<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">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saif</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Mohammad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This article describes the strategy submitted by the CiTIUS-COLE team to SemEval 2019 Task 5, a task which consists of binary classi- fication where the system predicting whether a tweet in English or in Spanish is hateful against women or immigrants or not. The proposed strategy relies on combining linguis- tic features to improve the classifier’s perfor- mance. More precisely, the method combines textual and lexical features, embedding words with the bag of words in Term Frequency- Inverse Document Frequency (TF-IDF) repre- sentation. The system performance reaches about 81% F1 when it is applied to the training dataset, but its F1 drops to 36% on the official test dataset for the English and 64% for the Spanish language concerning the hate speech class</abstract>
<identifier type="citekey">almatarneh-etal-2019-citius</identifier>
<identifier type="doi">10.18653/v1/S19-2068</identifier>
<location>
<url>https://aclanthology.org/S19-2068/</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>387</start>
<end>390</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CiTIUS-COLE at SemEval-2019 Task 5: Combining Linguistic Features to Identify Hate Speech Against Immigrants and Women on Multilingual Tweets
%A Almatarneh, Sattam
%A Gamallo, Pablo
%A Pena, Francisco J. Ribadas
%Y May, Jonathan
%Y Shutova, Ekaterina
%Y Herbelot, Aurelie
%Y Zhu, Xiaodan
%Y Apidianaki, Marianna
%Y Mohammad, Saif M.
%S Proceedings of the 13th International Workshop on Semantic Evaluation
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota, USA
%F almatarneh-etal-2019-citius
%X This article describes the strategy submitted by the CiTIUS-COLE team to SemEval 2019 Task 5, a task which consists of binary classi- fication where the system predicting whether a tweet in English or in Spanish is hateful against women or immigrants or not. The proposed strategy relies on combining linguis- tic features to improve the classifier’s perfor- mance. More precisely, the method combines textual and lexical features, embedding words with the bag of words in Term Frequency- Inverse Document Frequency (TF-IDF) repre- sentation. The system performance reaches about 81% F1 when it is applied to the training dataset, but its F1 drops to 36% on the official test dataset for the English and 64% for the Spanish language concerning the hate speech class
%R 10.18653/v1/S19-2068
%U https://aclanthology.org/S19-2068/
%U https://doi.org/10.18653/v1/S19-2068
%P 387-390
Markdown (Informal)
[CiTIUS-COLE at SemEval-2019 Task 5: Combining Linguistic Features to Identify Hate Speech Against Immigrants and Women on Multilingual Tweets](https://aclanthology.org/S19-2068/) (Almatarneh et al., SemEval 2019)
ACL