Arabic Language Sentiment Analysis on Health Services

Abdulaziz Alayba; Vasile Palade; Matthew England; Rahat Iqbal

doi:10.1109/ASAR.2017.8067771

Arabic Language Sentiment Analysis on Health Services

Abdulaziz Alayba, Vasile Palade, Matthew England, Rahat Iqbal

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

177 Downloads (Pure)

Abstract

The social media network phenomenon creates massive amounts of valuable data that is available online and easy to access. Many users share images, videos, comments, reviews, news and opinions on different social networks sites, with Twitter being one of the most popular ones. Data collected from Twitter is highly unstructured, and extracting useful information from tweets is a challenging task. Twitter has a huge number of Arabic users who mostly post and write their tweets using the Arabic language. While there has been a lot of research on sentiment analysis in English, the amount of researches and datasets in Arabic language is limited.

This paper introduces an Arabic language dataset, which is about opinions on health services and has been collected from Twitter. The paper will first detail the process of collecting the data from Twitter and also the process of filtering, pre-processing and annotating the Arabic text in order to build a big sentiment analysis dataset in Arabic. Several Machine Learning algorithms (Naïve Bayes, Support Vector Machine and Logistic Regression) alongside Deep and Convolutional Neural Networks were utilized in our experiments of sentiment analysis on our health dataset.

Publisher Statement: © 2017 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.

Original language	English
Title of host publication	2017 1st International Workshop on Arabic Script Analysis and Recognition (ASAR)
Publisher	IEEE Computer Society
Pages	114-118
Number of pages	5
ISBN (Electronic)	978-1-5090-6628-5
ISBN (Print)	978-1-5090-6629-2
DOIs	https://doi.org/10.1109/ASAR.2017.8067771
Publication status	Published - 16 Oct 2017
Event	International Workshop on Arabic and derived Script Analysis and Recognition - University Lorraine, Nancy, France Duration: 3 Apr 2017 → 5 Apr 2017 Conference number: 1 http://www.teklia.com/?p=220

Workshop

Workshop	International Workshop on Arabic and derived Script Analysis and Recognition
Abbreviated title	ASAR
Country/Territory	France
City	Nancy
Period	3/04/17 → 5/04/17
Internet address	http://www.teklia.com/?p=220

Keywords

Twitter
Sentiment analysis
Filtering
Feature extraction
Support vector machines
Semantics
Neural networks
Bayes methods
Big Data
data mining
learning (artificial intelligence)
neural nets
pattern classification
regression analysis
sentiment analysis
social networking (online)
support vector machines
Arabic language sentiment analysis
health services
social media network phenomenon
tweets
Arabic language dataset
big sentiment analysis dataset
Convolutional Neural Networks
health dataset
Arabic text filtering
Arabic text annotation
Arabic text preprocessing
machine learning algorithms
naïve Bayes algorithm
support vector machine algorithm
logistic regression algorithm
deep neural network
Sentiment Analysis
Machine Learning
Deep Neural NEtworks
Arabic Language

Access to Document

10.1109/ASAR.2017.8067771Licence: Unspecified

Post-PrintAccepted author manuscript, 965 KB

Cite this

@inproceedings{a1f79b911b954b5389f2ffd45588f6d6,

title = "Arabic Language Sentiment Analysis on Health Services",

abstract = "The social media network phenomenon creates massive amounts of valuable data that is available online and easy to access. Many users share images, videos, comments, reviews, news and opinions on different social networks sites, with Twitter being one of the most popular ones. Data collected from Twitter is highly unstructured, and extracting useful information from tweets is a challenging task. Twitter has a huge number of Arabic users who mostly post and write their tweets using the Arabic language. While there has been a lot of research on sentiment analysis in English, the amount of researches and datasets in Arabic language is limited. This paper introduces an Arabic language dataset, which is about opinions on health services and has been collected from Twitter. The paper will first detail the process of collecting the data from Twitter and also the process of filtering, pre-processing and annotating the Arabic text in order to build a big sentiment analysis dataset in Arabic. Several Machine Learning algorithms (Na{\"i}ve Bayes, Support Vector Machine and Logistic Regression) alongside Deep and Convolutional Neural Networks were utilized in our experiments of sentiment analysis on our health dataset. Publisher Statement: {\textcopyright} 2017 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 = "Twitter, Sentiment analysis, Filtering, Feature extraction, Support vector machines, Semantics, Neural networks, Bayes methods, Big Data, data mining, learning (artificial intelligence), neural nets, pattern classification, regression analysis, sentiment analysis, social networking (online), support vector machines, Arabic language sentiment analysis, health services, social media network phenomenon, tweets, Arabic language dataset, big sentiment analysis dataset, Convolutional Neural Networks, health dataset, Arabic text filtering, Arabic text annotation, Arabic text preprocessing, machine learning algorithms, na{\"i}ve Bayes algorithm, support vector machine algorithm, logistic regression algorithm, deep neural network, Sentiment Analysis, Machine Learning, Deep Neural NEtworks, Arabic Language",

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

year = "2017",

month = oct,

day = "16",

doi = "10.1109/ASAR.2017.8067771",

language = "English",

isbn = "978-1-5090-6629-2",

pages = "114--118",

booktitle = "2017 1st International Workshop on Arabic Script Analysis and Recognition (ASAR)",

publisher = "IEEE Computer Society",

address = "United States",

note = "International Workshop on Arabic and derived Script Analysis and Recognition, ASAR ; Conference date: 03-04-2017 Through 05-04-2017",

url = "http://www.teklia.com/?p=220",

}

TY - GEN

T1 - Arabic Language Sentiment Analysis on Health Services

AU - Alayba, Abdulaziz

AU - Palade, Vasile

AU - England, Matthew

AU - Iqbal, Rahat

N1 - Conference code: 1

PY - 2017/10/16

Y1 - 2017/10/16

N2 - The social media network phenomenon creates massive amounts of valuable data that is available online and easy to access. Many users share images, videos, comments, reviews, news and opinions on different social networks sites, with Twitter being one of the most popular ones. Data collected from Twitter is highly unstructured, and extracting useful information from tweets is a challenging task. Twitter has a huge number of Arabic users who mostly post and write their tweets using the Arabic language. While there has been a lot of research on sentiment analysis in English, the amount of researches and datasets in Arabic language is limited. This paper introduces an Arabic language dataset, which is about opinions on health services and has been collected from Twitter. The paper will first detail the process of collecting the data from Twitter and also the process of filtering, pre-processing and annotating the Arabic text in order to build a big sentiment analysis dataset in Arabic. Several Machine Learning algorithms (Naïve Bayes, Support Vector Machine and Logistic Regression) alongside Deep and Convolutional Neural Networks were utilized in our experiments of sentiment analysis on our health dataset. Publisher Statement: © 2017 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.

AB - The social media network phenomenon creates massive amounts of valuable data that is available online and easy to access. Many users share images, videos, comments, reviews, news and opinions on different social networks sites, with Twitter being one of the most popular ones. Data collected from Twitter is highly unstructured, and extracting useful information from tweets is a challenging task. Twitter has a huge number of Arabic users who mostly post and write their tweets using the Arabic language. While there has been a lot of research on sentiment analysis in English, the amount of researches and datasets in Arabic language is limited. This paper introduces an Arabic language dataset, which is about opinions on health services and has been collected from Twitter. The paper will first detail the process of collecting the data from Twitter and also the process of filtering, pre-processing and annotating the Arabic text in order to build a big sentiment analysis dataset in Arabic. Several Machine Learning algorithms (Naïve Bayes, Support Vector Machine and Logistic Regression) alongside Deep and Convolutional Neural Networks were utilized in our experiments of sentiment analysis on our health dataset. Publisher Statement: © 2017 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.

KW - Twitter

KW - Sentiment analysis

KW - Filtering

KW - Feature extraction

KW - Support vector machines

KW - Semantics

KW - Neural networks

KW - Bayes methods

KW - Big Data

KW - data mining

KW - learning (artificial intelligence)

KW - neural nets

KW - pattern classification

KW - regression analysis

KW - sentiment analysis

KW - social networking (online)

KW - support vector machines

KW - Arabic language sentiment analysis

KW - health services

KW - social media network phenomenon

KW - tweets

KW - Arabic language dataset

KW - big sentiment analysis dataset

KW - Convolutional Neural Networks

KW - health dataset

KW - Arabic text filtering

KW - Arabic text annotation

KW - Arabic text preprocessing

KW - machine learning algorithms

KW - naïve Bayes algorithm

KW - support vector machine algorithm

KW - logistic regression algorithm

KW - deep neural network

KW - Sentiment Analysis

KW - Machine Learning

KW - Deep Neural NEtworks

KW - Arabic Language

U2 - 10.1109/ASAR.2017.8067771

DO - 10.1109/ASAR.2017.8067771

M3 - Conference proceeding

SN - 978-1-5090-6629-2

SP - 114

EP - 118

BT - 2017 1st International Workshop on Arabic Script Analysis and Recognition (ASAR)

PB - IEEE Computer Society

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

Y2 - 3 April 2017 through 5 April 2017

ER -

Arabic Language Sentiment Analysis on Health Services

Abstract

Workshop

Keywords

Access to Document

Fingerprint

Cite this