Cover Image

TWEERIFY: A Web-Based Sentiment Analysis System Using Rule and Deep Learning Techniques

Social media platforms have ceased to be a platform for interaction and entertainment alone, and they have become a platform where citizens express their opinions about issues that affect them. In recent years, it has become a powerful platform where elections are won and lost. Therefore, organizati...

Full description

Saved in:
Bibliographic Details
Main Authors: Akande, O.N., Nnaemeka, E.S., Abikoye, O.C., Akande, H.B., Balogun, A., Ayoola, J.
Format: Article
Published: Springer Science and Business Media Deutschland GmbH 2022
Online Access:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85126387294&doi=10.1007%2f978-981-16-7182-1_7&partnerID=40&md5=ce0d21803feb37359ddbd72ab7133f8e
http://eprints.utp.edu.my/29079/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utp.eprints.29079
record_format eprints
spelling my.utp.eprints.290792022-03-24T09:21:51Z TWEERIFY: A Web-Based Sentiment Analysis System Using Rule and Deep Learning Techniques Akande, O.N. Nnaemeka, E.S. Abikoye, O.C. Akande, H.B. Balogun, A. Ayoola, J. Social media platforms have ceased to be a platform for interaction and entertainment alone, and they have become a platform where citizens express their opinions about issues that affect them. In recent years, it has become a powerful platform where elections are won and lost. Therefore, organizations and governments are increasingly interested in citizen�s views expressed on social media platforms. This research presents a novel approach to carry out aspect-level sentiment analysis of users� tweets using rule and convolutional neural network (CNN)-based deep learning technique. The rule-based technique was used to detect and extract sentiments from preprocessed tweets, while the CNN-based deep learning technique was employed for the sentiment polarity classification. A total of 26,378 tweets collected using �security� and �Nigeria� keywords were used to test the proposed model. The proposed model outperformed existing state-of-the-arts GloVe and word2vec models with an accuracy of 82.31, recall value of 82.21, precision value of 82.75 and F1 score of 81.89. The better performance of the proposed techniques could be as a result of the rule-based techniques that was introduced to capture sentiments expressed in slangs or informal languages which GloVe and word2vec have not been designed to capture. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. Springer Science and Business Media Deutschland GmbH 2022 Article NonPeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-85126387294&doi=10.1007%2f978-981-16-7182-1_7&partnerID=40&md5=ce0d21803feb37359ddbd72ab7133f8e Akande, O.N. and Nnaemeka, E.S. and Abikoye, O.C. and Akande, H.B. and Balogun, A. and Ayoola, J. (2022) TWEERIFY: A Web-Based Sentiment Analysis System Using Rule and Deep Learning Techniques. Lecture Notes on Data Engineering and Communications Technologies, 99 . pp. 75-87. http://eprints.utp.edu.my/29079/
institution Universiti Teknologi Petronas
building UTP Resource Centre
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Petronas
content_source UTP Institutional Repository
url_provider http://eprints.utp.edu.my/
description Social media platforms have ceased to be a platform for interaction and entertainment alone, and they have become a platform where citizens express their opinions about issues that affect them. In recent years, it has become a powerful platform where elections are won and lost. Therefore, organizations and governments are increasingly interested in citizen�s views expressed on social media platforms. This research presents a novel approach to carry out aspect-level sentiment analysis of users� tweets using rule and convolutional neural network (CNN)-based deep learning technique. The rule-based technique was used to detect and extract sentiments from preprocessed tweets, while the CNN-based deep learning technique was employed for the sentiment polarity classification. A total of 26,378 tweets collected using �security� and �Nigeria� keywords were used to test the proposed model. The proposed model outperformed existing state-of-the-arts GloVe and word2vec models with an accuracy of 82.31, recall value of 82.21, precision value of 82.75 and F1 score of 81.89. The better performance of the proposed techniques could be as a result of the rule-based techniques that was introduced to capture sentiments expressed in slangs or informal languages which GloVe and word2vec have not been designed to capture. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
format Article
author Akande, O.N.
Nnaemeka, E.S.
Abikoye, O.C.
Akande, H.B.
Balogun, A.
Ayoola, J.
spellingShingle Akande, O.N.
Nnaemeka, E.S.
Abikoye, O.C.
Akande, H.B.
Balogun, A.
Ayoola, J.
TWEERIFY: A Web-Based Sentiment Analysis System Using Rule and Deep Learning Techniques
author_facet Akande, O.N.
Nnaemeka, E.S.
Abikoye, O.C.
Akande, H.B.
Balogun, A.
Ayoola, J.
author_sort Akande, O.N.
title TWEERIFY: A Web-Based Sentiment Analysis System Using Rule and Deep Learning Techniques
title_short TWEERIFY: A Web-Based Sentiment Analysis System Using Rule and Deep Learning Techniques
title_full TWEERIFY: A Web-Based Sentiment Analysis System Using Rule and Deep Learning Techniques
title_fullStr TWEERIFY: A Web-Based Sentiment Analysis System Using Rule and Deep Learning Techniques
title_full_unstemmed TWEERIFY: A Web-Based Sentiment Analysis System Using Rule and Deep Learning Techniques
title_sort tweerify: a web-based sentiment analysis system using rule and deep learning techniques
publisher Springer Science and Business Media Deutschland GmbH
publishDate 2022
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85126387294&doi=10.1007%2f978-981-16-7182-1_7&partnerID=40&md5=ce0d21803feb37359ddbd72ab7133f8e
http://eprints.utp.edu.my/29079/
_version_ 1738656914876661760
score 13.211869

Similar Items