Sentiment analysis of reviews in natural language: Roman Urdu as a case study

Muhammad Aasim Qureshi; Muhammad Asif; Mohd Fadzil Hassan; Adnan Abid; Asad Kamal; Sohail Safdar; Rehan Akber

doi:10.1109/ACCESS.2022.3150172

Sentiment analysis of reviews in natural language: Roman Urdu as a case study

Muhammad Aasim Qureshi^*, Muhammad Asif^*, Mohd Fadzil Hassan^*, Adnan Abid, Asad Kamal, Sohail Safdar, Rehan Akber

^*Corresponding author for this work

School of Computing

Research output: Contribution to journal › Article › peer-review

45 Downloads (Pure)

Abstract

Opinion Mining from user reviews is an emerging field. Sentiment Analysis of Natural Language helps us in finding the opinion of the customers. These reviews can be in any language e.g. English, Chinese, Arabic, Japanese, Urdu, and Hindi. This research presents a model to classify the polarity of the review(s) in Roman Urdu (reviews). For the purpose, raw data was scraped from the reviews of 20 songs from Indo-Pak Music Industry. In this research a new dataset of 24000 reviews of Roman Urdu is created. Nine Machine Learning algorithms - Naïve Bayes, Support Vector Machine, Logistic Regression, K-Nearest Neighbors, Artificial Neural Networks, Convolutional Neural Network, Recurrent Neural Networks, ID3 and Gradient Boost Tree, are attempted. Logistic Regression outperformed the rest, based on testing and cross validation accuracies that are 92.25% and 91.47% respectively.

Original language	English
Pages (from-to)	24945-24954
Number of pages	10
Journal	IEEE Access
Volume	10
DOIs	https://doi.org/10.1109/ACCESS.2022.3150172
Publication status	Published - 15 Feb 2022

Keywords

ANN
classification
CNN
decision tree
deep learning
K-NN
machine learning
NaÃ¯ve Bayes
RNN
Roman Urdu
Roman Urdu corpus
Sentiment analysis
sentiment classification
song reviews
supervised learning

Access to Document

10.1109/ACCESS.2022.3150172

Sentiment analysis of reviews in natural languageFinal published version, 1.25 MBLicence: CC BY

Cite this

@article{fd35a036722e48b5946428b7edde9b83,

title = "Sentiment analysis of reviews in natural language: Roman Urdu as a case study",

abstract = "Opinion Mining from user reviews is an emerging field. Sentiment Analysis of Natural Language helps us in finding the opinion of the customers. These reviews can be in any language e.g. English, Chinese, Arabic, Japanese, Urdu, and Hindi. This research presents a model to classify the polarity of the review(s) in Roman Urdu (reviews). For the purpose, raw data was scraped from the reviews of 20 songs from Indo-Pak Music Industry. In this research a new dataset of 24000 reviews of Roman Urdu is created. Nine Machine Learning algorithms - Na{\"i}ve Bayes, Support Vector Machine, Logistic Regression, K-Nearest Neighbors, Artificial Neural Networks, Convolutional Neural Network, Recurrent Neural Networks, ID3 and Gradient Boost Tree, are attempted. Logistic Regression outperformed the rest, based on testing and cross validation accuracies that are 92.25% and 91.47% respectively.",

keywords = "ANN, classification, CNN, decision tree, deep learning, K-NN, machine learning, Na{\~A}¯ve Bayes, RNN, Roman Urdu, Roman Urdu corpus, Sentiment analysis, sentiment classification, song reviews, supervised learning",

author = "Qureshi, {Muhammad Aasim} and Muhammad Asif and Hassan, {Mohd Fadzil} and Adnan Abid and Asad Kamal and Sohail Safdar and Rehan Akber",

note = "Publisher Copyright: {\textcopyright} 2013 IEEE.",

year = "2022",

month = feb,

day = "15",

doi = "10.1109/ACCESS.2022.3150172",

language = "English",

volume = "10",

pages = "24945--24954",

journal = "IEEE Access",

issn = "2169-3536",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Sentiment analysis of reviews in natural language

T2 - Roman Urdu as a case study

AU - Qureshi, Muhammad Aasim

AU - Asif, Muhammad

AU - Hassan, Mohd Fadzil

AU - Abid, Adnan

AU - Kamal, Asad

AU - Safdar, Sohail

AU - Akber, Rehan

PY - 2022/2/15

Y1 - 2022/2/15

N2 - Opinion Mining from user reviews is an emerging field. Sentiment Analysis of Natural Language helps us in finding the opinion of the customers. These reviews can be in any language e.g. English, Chinese, Arabic, Japanese, Urdu, and Hindi. This research presents a model to classify the polarity of the review(s) in Roman Urdu (reviews). For the purpose, raw data was scraped from the reviews of 20 songs from Indo-Pak Music Industry. In this research a new dataset of 24000 reviews of Roman Urdu is created. Nine Machine Learning algorithms - Naïve Bayes, Support Vector Machine, Logistic Regression, K-Nearest Neighbors, Artificial Neural Networks, Convolutional Neural Network, Recurrent Neural Networks, ID3 and Gradient Boost Tree, are attempted. Logistic Regression outperformed the rest, based on testing and cross validation accuracies that are 92.25% and 91.47% respectively.

AB - Opinion Mining from user reviews is an emerging field. Sentiment Analysis of Natural Language helps us in finding the opinion of the customers. These reviews can be in any language e.g. English, Chinese, Arabic, Japanese, Urdu, and Hindi. This research presents a model to classify the polarity of the review(s) in Roman Urdu (reviews). For the purpose, raw data was scraped from the reviews of 20 songs from Indo-Pak Music Industry. In this research a new dataset of 24000 reviews of Roman Urdu is created. Nine Machine Learning algorithms - Naïve Bayes, Support Vector Machine, Logistic Regression, K-Nearest Neighbors, Artificial Neural Networks, Convolutional Neural Network, Recurrent Neural Networks, ID3 and Gradient Boost Tree, are attempted. Logistic Regression outperformed the rest, based on testing and cross validation accuracies that are 92.25% and 91.47% respectively.

KW - ANN

KW - classification

KW - CNN

KW - decision tree

KW - deep learning

KW - K-NN

KW - machine learning

KW - NaÃ¯ve Bayes

KW - RNN

KW - Roman Urdu

KW - Roman Urdu corpus

KW - Sentiment analysis

KW - sentiment classification

KW - song reviews

KW - supervised learning

UR - http://www.scopus.com/inward/record.url?scp=85124833996&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2022.3150172

DO - 10.1109/ACCESS.2022.3150172

M3 - Article

AN - SCOPUS:85124833996

SN - 2169-3536

VL - 10

SP - 24945

EP - 24954

JO - IEEE Access

JF - IEEE Access

ER -

Sentiment analysis of reviews in natural language: Roman Urdu as a case study

Abstract

Keywords

Access to Document

Fingerprint

Cite this