A convolutional stacked bidirectional LSTM with a multiplicative attention mechanism for aspect category and sentiment detection

Traditionally, sentiment analysis is a binary classification task that aims to categorize a piece of text as positive or negative. This approach, however, can be too simplistic when the text under scrutiny contains more than one opinion target. Hence, aspect-based sentiment analysis provides fine-gr...

Full description

Saved in:
Bibliographic Details
Main Authors: Kumar, Ashok J., Trueman, Tina Esther, Cambria, Erik
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2022
Subjects:
Online Access:https://hdl.handle.net/10356/160176
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-160176
record_format dspace
spelling sg-ntu-dr.10356-1601762022-07-14T03:54:16Z A convolutional stacked bidirectional LSTM with a multiplicative attention mechanism for aspect category and sentiment detection Kumar, Ashok J. Trueman, Tina Esther Cambria, Erik School of Computer Science and Engineering Engineering::Computer science and engineering Aspect-Based Sentiment Analysis Attention Mechanism Traditionally, sentiment analysis is a binary classification task that aims to categorize a piece of text as positive or negative. This approach, however, can be too simplistic when the text under scrutiny contains more than one opinion target. Hence, aspect-based sentiment analysis provides fine-grained sentiment understanding of the product, service, or policy. Machine learning and deep learning algorithms play an important role in this kind of task. Also, attention mechanism has shown breakthrough in the field of natural language processing. Therefore, we propose a convolutional stacked bidirectional long short-term memory with a multiplicative attention mechanism for aspect category and sentiment polarity detection. More specifically, we treat the proposed model as a multiclass classification problem. The proposed model is evaluated using SemEval-2015 and SemEval-2016 dataset. Our proposed model outperforms state-of-the-art results in aspect-based sentiment analysis. Agency for Science, Technology and Research (A*STAR) This research is supported by the Agency for Science, Technology and Research (A*STAR), under its AME Programmatic Funding Scheme (Project #A18A2b0046). We also thank the University Grants Commission, Government of India, for supporting this work under the UGC National Fellowship. 2022-07-14T03:54:16Z 2022-07-14T03:54:16Z 2021 Journal Article Kumar, A. J., Trueman, T. E. & Cambria, E. (2021). A convolutional stacked bidirectional LSTM with a multiplicative attention mechanism for aspect category and sentiment detection. Cognitive Computation, 13(6), 1423-1432. https://dx.doi.org/10.1007/s12559-021-09948-0 1866-9956 https://hdl.handle.net/10356/160176 10.1007/s12559-021-09948-0 2-s2.0-85118261543 6 13 1423 1432 en A18A2b0046 Cognitive Computation © 2021 The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature. 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
Aspect-Based Sentiment Analysis
Attention Mechanism
spellingShingle Engineering::Computer science and engineering
Aspect-Based Sentiment Analysis
Attention Mechanism
Kumar, Ashok J.
Trueman, Tina Esther
Cambria, Erik
A convolutional stacked bidirectional LSTM with a multiplicative attention mechanism for aspect category and sentiment detection
description Traditionally, sentiment analysis is a binary classification task that aims to categorize a piece of text as positive or negative. This approach, however, can be too simplistic when the text under scrutiny contains more than one opinion target. Hence, aspect-based sentiment analysis provides fine-grained sentiment understanding of the product, service, or policy. Machine learning and deep learning algorithms play an important role in this kind of task. Also, attention mechanism has shown breakthrough in the field of natural language processing. Therefore, we propose a convolutional stacked bidirectional long short-term memory with a multiplicative attention mechanism for aspect category and sentiment polarity detection. More specifically, we treat the proposed model as a multiclass classification problem. The proposed model is evaluated using SemEval-2015 and SemEval-2016 dataset. Our proposed model outperforms state-of-the-art results in aspect-based sentiment analysis.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Kumar, Ashok J.
Trueman, Tina Esther
Cambria, Erik
format Article
author Kumar, Ashok J.
Trueman, Tina Esther
Cambria, Erik
author_sort Kumar, Ashok J.
title A convolutional stacked bidirectional LSTM with a multiplicative attention mechanism for aspect category and sentiment detection
title_short A convolutional stacked bidirectional LSTM with a multiplicative attention mechanism for aspect category and sentiment detection
title_full A convolutional stacked bidirectional LSTM with a multiplicative attention mechanism for aspect category and sentiment detection
title_fullStr A convolutional stacked bidirectional LSTM with a multiplicative attention mechanism for aspect category and sentiment detection
title_full_unstemmed A convolutional stacked bidirectional LSTM with a multiplicative attention mechanism for aspect category and sentiment detection
title_sort convolutional stacked bidirectional lstm with a multiplicative attention mechanism for aspect category and sentiment detection
publishDate 2022
url https://hdl.handle.net/10356/160176
_version_ 1738844933773590528