Improving Sentiment Analysis in Arabic Using Word Representation

Abdulaziz Alayba; Vasile Palade; Matthew England; Rahat Iqbal

doi:10.1109/ASAR.2018.8480191

Improving Sentiment Analysis in Arabic Using Word Representation

Abdulaziz Alayba, Vasile Palade, Matthew England, Rahat Iqbal

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding › peer-review

68 Citations (Scopus)

205 Downloads (Pure)

Abstract

The complexities of Arabic language in morphology, orthography and dialects makes sentiment analysis for Arabic more challenging. Also, text feature extraction from short messages like tweets, in order to gauge the sentiment, makes this task even more difficult. In recent years, deep neural networks were often employed and showed very good results in sentiment classification and natural language processing applications. Word embedding, or word distributing approach, is a current and powerful tool to capture together the closest words from a contextual text. In this paper, we describe how we construct Word2Vec models from a large Arabic corpus obtained from ten newspapers in different Arab countries. By applying different machine learning algorithms and convolutional neural networks with different text feature selections, we report improved accuracy of sentiment classification (91%-95%) on our publicly available Arabic language health sentiment dataset [1]. Keywords - Arabic Sentiment Analysis, Machine Learning, Convolutional Neural Networks, Word Embedding, Word2Vec for Arabic, Lexicon.

Original language	English
Title of host publication	Proc. 2nd International Workshop on Arabic Script Analysis and Recognition (ASAR '18)
Publisher	IEEE Computer Society
Pages	13-18
Number of pages	6
ISBN (Electronic)	978-1-5386-1459-4
ISBN (Print)	978-1-5386-1460-0
DOIs	https://doi.org/10.1109/ASAR.2018.8480191
Publication status	Published - 4 Oct 2018
Event	IEEE International Workshop on Arabic and derived Script Analysis and Recognition - London, United Kingdom Duration: 12 Mar 2018 → 14 Mar 2018 Conference number: 2 http://asar.ieee.tn/

Workshop

Workshop	IEEE International Workshop on Arabic and derived Script Analysis and Recognition
Abbreviated title	ASAR
Country/Territory	United Kingdom
City	London
Period	12/03/18 → 14/03/18
Internet address	http://asar.ieee.tn/

Bibliographical note

© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Keywords

Arabic Sentiment Analysis
Machine Learning
Convolutional Neural Networks
Word Embedding
Word2Vec for Arabic
Lexicon

Access to Document

10.1109/ASAR.2018.8480191

Post-printAccepted author manuscript, 1.69 MBLicence: CC BY

Cite this

Alayba, A, Palade, V , England, M & Iqbal, R 2018, Improving Sentiment Analysis in Arabic Using Word Representation. in Proc. 2nd International Workshop on Arabic Script Analysis and Recognition (ASAR '18). IEEE Computer Society, pp. 13-18, IEEE International Workshop on Arabic and derived Script Analysis and Recognition, London, United Kingdom, 12/03/18. https://doi.org/10.1109/ASAR.2018.8480191

@inproceedings{a96670e30392494ca0110c4e2f0ea35d,

title = "Improving Sentiment Analysis in Arabic Using Word Representation",

abstract = "The complexities of Arabic language in morphology, orthography and dialects makes sentiment analysis for Arabic more challenging. Also, text feature extraction from short messages like tweets, in order to gauge the sentiment, makes this task even more difficult. In recent years, deep neural networks were often employed and showed very good results in sentiment classification and natural language processing applications. Word embedding, or word distributing approach, is a current and powerful tool to capture together the closest words from a contextual text. In this paper, we describe how we construct Word2Vec models from a large Arabic corpus obtained from ten newspapers in different Arab countries. By applying different machine learning algorithms and convolutional neural networks with different text feature selections, we report improved accuracy of sentiment classification (91%-95%) on our publicly available Arabic language health sentiment dataset [1]. Keywords - Arabic Sentiment Analysis, Machine Learning, Convolutional Neural Networks, Word Embedding, Word2Vec for Arabic, Lexicon.",

keywords = "Arabic Sentiment Analysis, Machine Learning, Convolutional Neural Networks, Word Embedding, Word2Vec for Arabic, Lexicon",

author = "Abdulaziz Alayba and Vasile Palade and Matthew England and Rahat Iqbal",

note = "{\textcopyright} 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.; IEEE International Workshop on Arabic and derived Script Analysis and Recognition, ASAR ; Conference date: 12-03-2018 Through 14-03-2018",

year = "2018",

month = oct,

day = "4",

doi = "10.1109/ASAR.2018.8480191",

language = "English",

isbn = " 978-1-5386-1460-0 ",

pages = "13--18",

booktitle = "Proc. 2nd International Workshop on Arabic Script Analysis and Recognition (ASAR '18)",

publisher = "IEEE Computer Society",

address = "United States",

url = "http://asar.ieee.tn/",

}

TY - GEN

T1 - Improving Sentiment Analysis in Arabic Using Word Representation

AU - Alayba, Abdulaziz

AU - Palade, Vasile

AU - England, Matthew

AU - Iqbal, Rahat

N1 - Conference code: 2

PY - 2018/10/4

Y1 - 2018/10/4

N2 - The complexities of Arabic language in morphology, orthography and dialects makes sentiment analysis for Arabic more challenging. Also, text feature extraction from short messages like tweets, in order to gauge the sentiment, makes this task even more difficult. In recent years, deep neural networks were often employed and showed very good results in sentiment classification and natural language processing applications. Word embedding, or word distributing approach, is a current and powerful tool to capture together the closest words from a contextual text. In this paper, we describe how we construct Word2Vec models from a large Arabic corpus obtained from ten newspapers in different Arab countries. By applying different machine learning algorithms and convolutional neural networks with different text feature selections, we report improved accuracy of sentiment classification (91%-95%) on our publicly available Arabic language health sentiment dataset [1]. Keywords - Arabic Sentiment Analysis, Machine Learning, Convolutional Neural Networks, Word Embedding, Word2Vec for Arabic, Lexicon.

AB - The complexities of Arabic language in morphology, orthography and dialects makes sentiment analysis for Arabic more challenging. Also, text feature extraction from short messages like tweets, in order to gauge the sentiment, makes this task even more difficult. In recent years, deep neural networks were often employed and showed very good results in sentiment classification and natural language processing applications. Word embedding, or word distributing approach, is a current and powerful tool to capture together the closest words from a contextual text. In this paper, we describe how we construct Word2Vec models from a large Arabic corpus obtained from ten newspapers in different Arab countries. By applying different machine learning algorithms and convolutional neural networks with different text feature selections, we report improved accuracy of sentiment classification (91%-95%) on our publicly available Arabic language health sentiment dataset [1]. Keywords - Arabic Sentiment Analysis, Machine Learning, Convolutional Neural Networks, Word Embedding, Word2Vec for Arabic, Lexicon.

KW - Arabic Sentiment Analysis

KW - Machine Learning

KW - Convolutional Neural Networks

KW - Word Embedding

KW - Word2Vec for Arabic

KW - Lexicon

U2 - 10.1109/ASAR.2018.8480191

DO - 10.1109/ASAR.2018.8480191

M3 - Conference proceeding

SN - 978-1-5386-1460-0

SP - 13

EP - 18

BT - Proc. 2nd International Workshop on Arabic Script Analysis and Recognition (ASAR '18)

PB - IEEE Computer Society

T2 - IEEE International Workshop on Arabic and derived Script Analysis and Recognition

Y2 - 12 March 2018 through 14 March 2018

ER -

Improving Sentiment Analysis in Arabic Using Word Representation

Abstract

Workshop

Bibliographical note

Keywords

Access to Document

Fingerprint

Cite this