Hybrid sentiment classification on twitter aspect-based sentiment analysis
Social media sites and applications, including Facebook, YouTube, Twitter and blogs, have become major social media attractions today. The huge amount of information from this medium has become an attractive resource for organisations to monitor the opinions of users, and therefore, it is receiving...
Saved in:
Main Authors: | , , |
---|---|
Format: | Article |
Published: |
Springer New York LLC
2018
|
Subjects: | |
Online Access: | http://eprints.utm.my/id/eprint/85709/ http://dx.doi.org/10.1007/s10489-017-1098-6 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.utm.85709 |
---|---|
record_format |
eprints |
spelling |
my.utm.857092020-07-22T02:34:36Z http://eprints.utm.my/id/eprint/85709/ Hybrid sentiment classification on twitter aspect-based sentiment analysis Zainuddin, Nurulhuda Selamat, Ali Ibrahim, Roliana QA75 Electronic computers. Computer science Social media sites and applications, including Facebook, YouTube, Twitter and blogs, have become major social media attractions today. The huge amount of information from this medium has become an attractive resource for organisations to monitor the opinions of users, and therefore, it is receiving a lot of attention in the field of sentiment analysis. Early work on sentiment analysis approached this problem at a document-level, where the overall sentiment was identified, rather than the details of the sentiment. This research took into account the use of an aspect-based sentiment analysis on Twitter in order to perform a finer-grained analysis. A new hybrid sentiment classification for Twitter is proposed by embedding a feature selection method. A comparison of the accuracy of the classification by the principal component analysis (PCA), latent semantic analysis (LSA), and random projection (RP) feature selection methods are presented in this paper. Furthermore, the hybrid sentiment classification was validated using Twitter datasets to represent different domains, and the evaluation with different classification algorithms also demonstrated that the new hybrid approach produced meaningful results. The implementations showed that the new hybrid sentiment classification was able to improve the accuracy performance from the existing baseline sentiment classification methods by 76.55, 71.62 and 74.24%, respectively. Springer New York LLC 2018-05 Article PeerReviewed Zainuddin, Nurulhuda and Selamat, Ali and Ibrahim, Roliana (2018) Hybrid sentiment classification on twitter aspect-based sentiment analysis. Applied Intelligence, 48 (5). pp. 1218-1232. ISSN 0924-669X http://dx.doi.org/10.1007/s10489-017-1098-6 |
institution |
Universiti Teknologi Malaysia |
building |
UTM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Teknologi Malaysia |
content_source |
UTM Institutional Repository |
url_provider |
http://eprints.utm.my/ |
topic |
QA75 Electronic computers. Computer science |
spellingShingle |
QA75 Electronic computers. Computer science Zainuddin, Nurulhuda Selamat, Ali Ibrahim, Roliana Hybrid sentiment classification on twitter aspect-based sentiment analysis |
description |
Social media sites and applications, including Facebook, YouTube, Twitter and blogs, have become major social media attractions today. The huge amount of information from this medium has become an attractive resource for organisations to monitor the opinions of users, and therefore, it is receiving a lot of attention in the field of sentiment analysis. Early work on sentiment analysis approached this problem at a document-level, where the overall sentiment was identified, rather than the details of the sentiment. This research took into account the use of an aspect-based sentiment analysis on Twitter in order to perform a finer-grained analysis. A new hybrid sentiment classification for Twitter is proposed by embedding a feature selection method. A comparison of the accuracy of the classification by the principal component analysis (PCA), latent semantic analysis (LSA), and random projection (RP) feature selection methods are presented in this paper. Furthermore, the hybrid sentiment classification was validated using Twitter datasets to represent different domains, and the evaluation with different classification algorithms also demonstrated that the new hybrid approach produced meaningful results. The implementations showed that the new hybrid sentiment classification was able to improve the accuracy performance from the existing baseline sentiment classification methods by 76.55, 71.62 and 74.24%, respectively. |
format |
Article |
author |
Zainuddin, Nurulhuda Selamat, Ali Ibrahim, Roliana |
author_facet |
Zainuddin, Nurulhuda Selamat, Ali Ibrahim, Roliana |
author_sort |
Zainuddin, Nurulhuda |
title |
Hybrid sentiment classification on twitter aspect-based sentiment analysis |
title_short |
Hybrid sentiment classification on twitter aspect-based sentiment analysis |
title_full |
Hybrid sentiment classification on twitter aspect-based sentiment analysis |
title_fullStr |
Hybrid sentiment classification on twitter aspect-based sentiment analysis |
title_full_unstemmed |
Hybrid sentiment classification on twitter aspect-based sentiment analysis |
title_sort |
hybrid sentiment classification on twitter aspect-based sentiment analysis |
publisher |
Springer New York LLC |
publishDate |
2018 |
url |
http://eprints.utm.my/id/eprint/85709/ http://dx.doi.org/10.1007/s10489-017-1098-6 |
_version_ |
1674066195970523136 |
score |
13.15806 |