A novel auto-annotation technique for aspect level sentiment analysis
In machine learning, sentiment analysis is a technique to find and analyze the sentiments hidden in the text. For sentiment analysis, annotated data is a basic requirement. Generally, this data is manually annotated. Manual annotation is time consuming, costly and laborious process. To overcome thes...
Saved in:
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Published: |
Tech Science Press
2022
|
Online Access: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85116978167&doi=10.32604%2fcmc.2022.020544&partnerID=40&md5=aed2a466cdb4768e746038efac162ce0 http://eprints.utp.edu.my/28891/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.utp.eprints.28891 |
---|---|
record_format |
eprints |
spelling |
my.utp.eprints.288912022-03-17T02:22:32Z A novel auto-annotation technique for aspect level sentiment analysis Qureshi, M.A. Asif, M. Hassan, M.F. Mustafa, G. Ehsan, M.K. Ali, A. Sajid, U. In machine learning, sentiment analysis is a technique to find and analyze the sentiments hidden in the text. For sentiment analysis, annotated data is a basic requirement. Generally, this data is manually annotated. Manual annotation is time consuming, costly and laborious process. To overcome these resource constraints this research has proposed a fully automated annotation technique for aspect level sentiment analysis. Dataset is created from the reviews of ten most popular songs on YouTube. Reviews of five aspects�voice, video, music, lyrics and song, are extracted. An N-Gram based technique is proposed. Complete dataset consists of 369436 reviews that took 173.53 s to annotate using the proposed technique while this dataset might have taken approximately 2.07 million seconds (575 h) if it was annotated manually. For the validation of the proposed technique, a sub-dataset�Voice, is annotated manually as well as with the proposed technique. Cohen�s Kappa statistics is used to evaluate the degree of agreement between the two annotations. The high Kappa value (i.e., 0.9571) shows the high level of agreement between the two. This validates that the quality of annotation of the proposed technique is as good as manual annotation even with far less computational cost. This research also contributes in consolidating the guidelines for the manual annotation process. © 2022 Tech Science Press. All rights reserved. Tech Science Press 2022 Article NonPeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-85116978167&doi=10.32604%2fcmc.2022.020544&partnerID=40&md5=aed2a466cdb4768e746038efac162ce0 Qureshi, M.A. and Asif, M. and Hassan, M.F. and Mustafa, G. and Ehsan, M.K. and Ali, A. and Sajid, U. (2022) A novel auto-annotation technique for aspect level sentiment analysis. Computers, Materials and Continua, 70 (3). pp. 4987-5004. http://eprints.utp.edu.my/28891/ |
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 |
In machine learning, sentiment analysis is a technique to find and analyze the sentiments hidden in the text. For sentiment analysis, annotated data is a basic requirement. Generally, this data is manually annotated. Manual annotation is time consuming, costly and laborious process. To overcome these resource constraints this research has proposed a fully automated annotation technique for aspect level sentiment analysis. Dataset is created from the reviews of ten most popular songs on YouTube. Reviews of five aspects�voice, video, music, lyrics and song, are extracted. An N-Gram based technique is proposed. Complete dataset consists of 369436 reviews that took 173.53 s to annotate using the proposed technique while this dataset might have taken approximately 2.07 million seconds (575 h) if it was annotated manually. For the validation of the proposed technique, a sub-dataset�Voice, is annotated manually as well as with the proposed technique. Cohen�s Kappa statistics is used to evaluate the degree of agreement between the two annotations. The high Kappa value (i.e., 0.9571) shows the high level of agreement between the two. This validates that the quality of annotation of the proposed technique is as good as manual annotation even with far less computational cost. This research also contributes in consolidating the guidelines for the manual annotation process. © 2022 Tech Science Press. All rights reserved. |
format |
Article |
author |
Qureshi, M.A. Asif, M. Hassan, M.F. Mustafa, G. Ehsan, M.K. Ali, A. Sajid, U. |
spellingShingle |
Qureshi, M.A. Asif, M. Hassan, M.F. Mustafa, G. Ehsan, M.K. Ali, A. Sajid, U. A novel auto-annotation technique for aspect level sentiment analysis |
author_facet |
Qureshi, M.A. Asif, M. Hassan, M.F. Mustafa, G. Ehsan, M.K. Ali, A. Sajid, U. |
author_sort |
Qureshi, M.A. |
title |
A novel auto-annotation technique for aspect level sentiment analysis |
title_short |
A novel auto-annotation technique for aspect level sentiment analysis |
title_full |
A novel auto-annotation technique for aspect level sentiment analysis |
title_fullStr |
A novel auto-annotation technique for aspect level sentiment analysis |
title_full_unstemmed |
A novel auto-annotation technique for aspect level sentiment analysis |
title_sort |
novel auto-annotation technique for aspect level sentiment analysis |
publisher |
Tech Science Press |
publishDate |
2022 |
url |
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85116978167&doi=10.32604%2fcmc.2022.020544&partnerID=40&md5=aed2a466cdb4768e746038efac162ce0 http://eprints.utp.edu.my/28891/ |
_version_ |
1738656897541603328 |
score |
13.160551 |