@inproceedings{mohammad-etal-2016-sentiment,
title = "Sentiment Lexicons for {A}rabic Social Media",
author = "Mohammad, Saif and
Salameh, Mohammad and
Kiritchenko, Svetlana",
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/L16-1006",
pages = "33--37",
abstract = "Existing Arabic sentiment lexicons have low coverage―with only a few thousand entries. In this paper, we present several large sentiment lexicons that were automatically generated using two different methods: (1) by using distant supervision techniques on Arabic tweets, and (2) by translating English sentiment lexicons into Arabic using a freely available statistical machine translation system. We compare the usefulness of new and old sentiment lexicons in the downstream application of sentence-level sentiment analysis. Our baseline sentiment analysis system uses numerous surface form features. Nonetheless, the system benefits from using additional features drawn from sentiment lexicons. The best result is obtained using the automatically generated Dialectal Hashtag Lexicon and the Arabic translations of the NRC Emotion Lexicon (accuracy of 66.6{\%}). Finally, we describe a qualitative study of the automatic translations of English sentiment lexicons into Arabic, which shows that about 88{\%} of the automatically translated entries are valid for English as well. Close to 10{\%} of the invalid entries are caused by gross mistranslations, close to 40{\%} by translations into a related word, and about 50{\%} by differences in how the word is used in Arabic.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mohammad-etal-2016-sentiment">
<titleInfo>
<title>Sentiment Lexicons for Arabic Social Media</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saif</namePart>
<namePart type="family">Mohammad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">Salameh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Svetlana</namePart>
<namePart type="family">Kiritchenko</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>Existing Arabic sentiment lexicons have low coverage―with only a few thousand entries. In this paper, we present several large sentiment lexicons that were automatically generated using two different methods: (1) by using distant supervision techniques on Arabic tweets, and (2) by translating English sentiment lexicons into Arabic using a freely available statistical machine translation system. We compare the usefulness of new and old sentiment lexicons in the downstream application of sentence-level sentiment analysis. Our baseline sentiment analysis system uses numerous surface form features. Nonetheless, the system benefits from using additional features drawn from sentiment lexicons. The best result is obtained using the automatically generated Dialectal Hashtag Lexicon and the Arabic translations of the NRC Emotion Lexicon (accuracy of 66.6%). Finally, we describe a qualitative study of the automatic translations of English sentiment lexicons into Arabic, which shows that about 88% of the automatically translated entries are valid for English as well. Close to 10% of the invalid entries are caused by gross mistranslations, close to 40% by translations into a related word, and about 50% by differences in how the word is used in Arabic.</abstract>
<identifier type="citekey">mohammad-etal-2016-sentiment</identifier>
<location>
<url>https://aclanthology.org/L16-1006</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>33</start>
<end>37</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sentiment Lexicons for Arabic Social Media
%A Mohammad, Saif
%A Salameh, Mohammad
%A Kiritchenko, Svetlana
%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 mohammad-etal-2016-sentiment
%X Existing Arabic sentiment lexicons have low coverage―with only a few thousand entries. In this paper, we present several large sentiment lexicons that were automatically generated using two different methods: (1) by using distant supervision techniques on Arabic tweets, and (2) by translating English sentiment lexicons into Arabic using a freely available statistical machine translation system. We compare the usefulness of new and old sentiment lexicons in the downstream application of sentence-level sentiment analysis. Our baseline sentiment analysis system uses numerous surface form features. Nonetheless, the system benefits from using additional features drawn from sentiment lexicons. The best result is obtained using the automatically generated Dialectal Hashtag Lexicon and the Arabic translations of the NRC Emotion Lexicon (accuracy of 66.6%). Finally, we describe a qualitative study of the automatic translations of English sentiment lexicons into Arabic, which shows that about 88% of the automatically translated entries are valid for English as well. Close to 10% of the invalid entries are caused by gross mistranslations, close to 40% by translations into a related word, and about 50% by differences in how the word is used in Arabic.
%U https://aclanthology.org/L16-1006
%P 33-37
Markdown (Informal)
[Sentiment Lexicons for Arabic Social Media](https://aclanthology.org/L16-1006) (Mohammad et al., LREC 2016)
ACL
- Saif Mohammad, Mohammad Salameh, and Svetlana Kiritchenko. 2016. Sentiment Lexicons for Arabic Social Media. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 33–37, Portorož, Slovenia. European Language Resources Association (ELRA).