Gender-based multi-aspect sentiment detection using multilabel learning
Sentiment analysis is an important task in the field of natural language processing that aims to gauge and predict people's opinions from large amounts of data. In particular, gender-based sentiment analysis can influence stakeholders and drug developers in real-world markets. In this work, we...
Saved in:
Main Authors: | , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/163883 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-163883 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1638832022-12-21T03:52:53Z Gender-based multi-aspect sentiment detection using multilabel learning Kumar, J. Ashok Trueman, Tina Esther Cambria, Erik School of Computer Science and Engineering Engineering::Computer science and engineering Multilabel Learning Gender-Based Sentiment Sentiment analysis is an important task in the field of natural language processing that aims to gauge and predict people's opinions from large amounts of data. In particular, gender-based sentiment analysis can influence stakeholders and drug developers in real-world markets. In this work, we present a gender-based multi-aspect sentiment detection model using multilabel learning algorithms. We divide Abilify and Celebrex datasets into three groups based on gender information, namely: male, female, and mixed. We then represent bag-of-words (BoW), term frequency-inverse document frequency (TF-IDF), and global vectors for word representation (GloVe) based features for each group. Next, we apply problem transformation approaches and multichannel recurrent neural networks with attention mechanism. Results show that traditional multilabel transformation methods achieve better performance for small amounts of data and long-range sequence in terms of samples and labels, and that deep learning models achieve better performance in terms of mean test accuracy, AUC Score, RL, and average precision using GloVe word embedding features in both datasets. This work was supported by the University Grants Commission (UGC), Government of India under the National Doctoral Fellowship. 2022-12-21T03:52:53Z 2022-12-21T03:52:53Z 2022 Journal Article Kumar, J. A., Trueman, T. E. & Cambria, E. (2022). Gender-based multi-aspect sentiment detection using multilabel learning. Information Sciences, 606, 453-468. https://dx.doi.org/10.1016/j.ins.2022.05.057 0020-0255 https://hdl.handle.net/10356/163883 10.1016/j.ins.2022.05.057 2-s2.0-85131094949 606 453 468 en Information Sciences © 2022 Elsevier Inc. All rights reserved. |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Computer science and engineering Multilabel Learning Gender-Based Sentiment |
spellingShingle |
Engineering::Computer science and engineering Multilabel Learning Gender-Based Sentiment Kumar, J. Ashok Trueman, Tina Esther Cambria, Erik Gender-based multi-aspect sentiment detection using multilabel learning |
description |
Sentiment analysis is an important task in the field of natural language processing that aims to gauge and predict people's opinions from large amounts of data. In particular, gender-based sentiment analysis can influence stakeholders and drug developers in real-world markets. In this work, we present a gender-based multi-aspect sentiment detection model using multilabel learning algorithms. We divide Abilify and Celebrex datasets into three groups based on gender information, namely: male, female, and mixed. We then represent bag-of-words (BoW), term frequency-inverse document frequency (TF-IDF), and global vectors for word representation (GloVe) based features for each group. Next, we apply problem transformation approaches and multichannel recurrent neural networks with attention mechanism. Results show that traditional multilabel transformation methods achieve better performance for small amounts of data and long-range sequence in terms of samples and labels, and that deep learning models achieve better performance in terms of mean test accuracy, AUC Score, RL, and average precision using GloVe word embedding features in both datasets. |
author2 |
School of Computer Science and Engineering |
author_facet |
School of Computer Science and Engineering Kumar, J. Ashok Trueman, Tina Esther Cambria, Erik |
format |
Article |
author |
Kumar, J. Ashok Trueman, Tina Esther Cambria, Erik |
author_sort |
Kumar, J. Ashok |
title |
Gender-based multi-aspect sentiment detection using multilabel learning |
title_short |
Gender-based multi-aspect sentiment detection using multilabel learning |
title_full |
Gender-based multi-aspect sentiment detection using multilabel learning |
title_fullStr |
Gender-based multi-aspect sentiment detection using multilabel learning |
title_full_unstemmed |
Gender-based multi-aspect sentiment detection using multilabel learning |
title_sort |
gender-based multi-aspect sentiment detection using multilabel learning |
publishDate |
2022 |
url |
https://hdl.handle.net/10356/163883 |
_version_ |
1753801188163190784 |