@inproceedings{el-beltagy-2016-nileulex,
title = "{N}ile{UL}ex: A Phrase and Word Level Sentiment Lexicon for {E}gyptian and {M}odern {S}tandard {A}rabic",
author = "El-Beltagy, Samhaa R.",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1463",
pages = "2900--2905",
abstract = "This paper presents NileULex, which is an Arabic sentiment lexicon containing close to six thousands Arabic words and compound phrases. Forty five percent of the terms and expressions in the lexicon are Egyptian or colloquial while fifty five percent are Modern Standard Arabic. While the collection of many of the terms included in the lexicon was done automatically, the actual addition of any term was done manually. One of the important criterions for adding terms to the lexicon, was that they be as unambiguous as possible. The result is a lexicon with a much higher quality than any translated variant or automatically constructed one. To demonstrate that a lexicon such as this can directly impact the task of sentiment analysis, a very basic machine learning based sentiment analyser that uses unigrams, bigrams, and lexicon based features was applied on two different Twitter datasets. The obtained results were compared to a baseline system that only uses unigrams and bigrams. The same lexicon based features were also generated using a publicly available translation of a popular sentiment lexicon. The experiments show that usage of the developed lexicon improves the results over both the baseline and the publicly available lexicon.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="el-beltagy-2016-nileulex">
<titleInfo>
<title>NileULex: A Phrase and Word Level Sentiment Lexicon for Egyptian and Modern Standard Arabic</title>
</titleInfo>
<name type="personal">
<namePart type="given">Samhaa</namePart>
<namePart type="given">R</namePart>
<namePart type="family">El-Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents NileULex, which is an Arabic sentiment lexicon containing close to six thousands Arabic words and compound phrases. Forty five percent of the terms and expressions in the lexicon are Egyptian or colloquial while fifty five percent are Modern Standard Arabic. While the collection of many of the terms included in the lexicon was done automatically, the actual addition of any term was done manually. One of the important criterions for adding terms to the lexicon, was that they be as unambiguous as possible. The result is a lexicon with a much higher quality than any translated variant or automatically constructed one. To demonstrate that a lexicon such as this can directly impact the task of sentiment analysis, a very basic machine learning based sentiment analyser that uses unigrams, bigrams, and lexicon based features was applied on two different Twitter datasets. The obtained results were compared to a baseline system that only uses unigrams and bigrams. The same lexicon based features were also generated using a publicly available translation of a popular sentiment lexicon. The experiments show that usage of the developed lexicon improves the results over both the baseline and the publicly available lexicon.</abstract>
<identifier type="citekey">el-beltagy-2016-nileulex</identifier>
<location>
<url>https://aclanthology.org/L16-1463</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>2900</start>
<end>2905</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NileULex: A Phrase and Word Level Sentiment Lexicon for Egyptian and Modern Standard Arabic
%A El-Beltagy, Samhaa R.
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F el-beltagy-2016-nileulex
%X This paper presents NileULex, which is an Arabic sentiment lexicon containing close to six thousands Arabic words and compound phrases. Forty five percent of the terms and expressions in the lexicon are Egyptian or colloquial while fifty five percent are Modern Standard Arabic. While the collection of many of the terms included in the lexicon was done automatically, the actual addition of any term was done manually. One of the important criterions for adding terms to the lexicon, was that they be as unambiguous as possible. The result is a lexicon with a much higher quality than any translated variant or automatically constructed one. To demonstrate that a lexicon such as this can directly impact the task of sentiment analysis, a very basic machine learning based sentiment analyser that uses unigrams, bigrams, and lexicon based features was applied on two different Twitter datasets. The obtained results were compared to a baseline system that only uses unigrams and bigrams. The same lexicon based features were also generated using a publicly available translation of a popular sentiment lexicon. The experiments show that usage of the developed lexicon improves the results over both the baseline and the publicly available lexicon.
%U https://aclanthology.org/L16-1463
%P 2900-2905
Markdown (Informal)
[NileULex: A Phrase and Word Level Sentiment Lexicon for Egyptian and Modern Standard Arabic](https://aclanthology.org/L16-1463) (El-Beltagy, LREC 2016)
ACL