Bayesian network based extreme learning machine for subjectivity detection
Subjectivity detection is a task of natural language processing that aims to remove ‘factual’ or ‘neutral’ content, i.e., objective text that does not contain any opinion, from online product reviews. Such a pre-processing step is crucial to increase the accuracy of sentiment analysis systems, as th...
Saved in:
Main Authors: | , , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2018
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/87262 http://hdl.handle.net/10220/44342 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-87262 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-872622020-03-07T11:48:56Z Bayesian network based extreme learning machine for subjectivity detection Chaturvedi, Iti Ragusa, Edoardo Gastaldo, Paolo Zunino, Rodolfo Cambria, Erik School of Computer Science and Engineering Extreme Learning Machine Subjectivity Detection Subjectivity detection is a task of natural language processing that aims to remove ‘factual’ or ‘neutral’ content, i.e., objective text that does not contain any opinion, from online product reviews. Such a pre-processing step is crucial to increase the accuracy of sentiment analysis systems, as these are usually optimized for the binary classification task of distinguishing between positive and negative content. In this paper, we extend the extreme learning machine (ELM) paradigm to a novel framework that exploits the features of both Bayesian networks and fuzzy recurrent neural networks to perform subjectivity detection. In particular, Bayesian networks are used to build a network of connections among the hidden neurons of the conventional ELM configuration in order to capture dependencies in high-dimensional data. Next, a fuzzy recurrent neural network inherits the overall structure generated by the Bayesian networks to model temporal features in the predictor. Experimental results confirmed the ability of the proposed framework to deal with standard subjectivity detection problems and also proved its capacity to address portability across languages in translation tasks. Accepted version 2018-01-24T07:28:07Z 2019-12-06T16:38:26Z 2018-01-24T07:28:07Z 2019-12-06T16:38:26Z 2017 Journal Article Chaturvedi, I., Ragusa, E., Gastaldo, P., Zunino, R., & Cambria, E. (2017). Bayesian network based extreme learning machine for subjectivity detection. Journal of the Franklin Institute, 355(4), 1780-1797. 0016-0032 https://hdl.handle.net/10356/87262 http://hdl.handle.net/10220/44342 10.1016/j.jfranklin.2017.06.007 en Journal of the Franklin Institute © 2017 The Franklin Institute (published by Elsevier). This is the author created version of a work that has been peer reviewed and accepted for publication in Journal of the Franklin Institute, published by Elsevier on behalf of The Franklin Institute. It incorporates referee’s comments but changes resulting from the publishing process, such as copyediting, structural formatting, may not be reflected in this document. The published version is available at: [http://dx.doi.org/10.1016/j.jfranklin.2017.06.007]. 35 p. application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
country |
Singapore |
collection |
DR-NTU |
language |
English |
topic |
Extreme Learning Machine Subjectivity Detection |
spellingShingle |
Extreme Learning Machine Subjectivity Detection Chaturvedi, Iti Ragusa, Edoardo Gastaldo, Paolo Zunino, Rodolfo Cambria, Erik Bayesian network based extreme learning machine for subjectivity detection |
description |
Subjectivity detection is a task of natural language processing that aims to remove ‘factual’ or ‘neutral’ content, i.e., objective text that does not contain any opinion, from online product reviews. Such a pre-processing step is crucial to increase the accuracy of sentiment analysis systems, as these are usually optimized for the binary classification task of distinguishing between positive and negative content. In this paper, we extend the extreme learning machine (ELM) paradigm to a novel framework that exploits the features of both Bayesian networks and fuzzy recurrent neural networks to perform subjectivity detection. In particular, Bayesian networks are used to build a network of connections among the hidden neurons of the conventional ELM configuration in order to capture dependencies in high-dimensional data. Next, a fuzzy recurrent neural network inherits the overall structure generated by the Bayesian networks to model temporal features in the predictor. Experimental results confirmed the ability of the proposed framework to deal with standard subjectivity detection problems and also proved its capacity to address portability across languages in translation tasks. |
author2 |
School of Computer Science and Engineering |
author_facet |
School of Computer Science and Engineering Chaturvedi, Iti Ragusa, Edoardo Gastaldo, Paolo Zunino, Rodolfo Cambria, Erik |
format |
Article |
author |
Chaturvedi, Iti Ragusa, Edoardo Gastaldo, Paolo Zunino, Rodolfo Cambria, Erik |
author_sort |
Chaturvedi, Iti |
title |
Bayesian network based extreme learning machine for subjectivity detection |
title_short |
Bayesian network based extreme learning machine for subjectivity detection |
title_full |
Bayesian network based extreme learning machine for subjectivity detection |
title_fullStr |
Bayesian network based extreme learning machine for subjectivity detection |
title_full_unstemmed |
Bayesian network based extreme learning machine for subjectivity detection |
title_sort |
bayesian network based extreme learning machine for subjectivity detection |
publishDate |
2018 |
url |
https://hdl.handle.net/10356/87262 http://hdl.handle.net/10220/44342 |
_version_ |
1681044011072094208 |