A hybrid deep learning architecture for opinion-oriented multi-document summarization based on multi-feature fusion

Opinion summarization is a process to produce concise summaries from a large number of opinionated texts. In this paper, we present a novel deep-learning-based method for the generic opinion-oriented extractive summarization of multi-documents (also known as RDLS). The method comprises sentiment ana...

Full description

Saved in:
Bibliographic Details
Main Authors: Abdi, Asad, Hasan, Shafaatunnur, Shamsuddin, Siti Mariyam, Idris, Norisma, Piran, Jalil
Format: Article
Published: Elsevier 2021
Subjects:
Online Access:http://eprints.um.edu.my/25976/
https://doi.org/10.1016/j.knosys.2020.106658
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.um.eprints.25976
record_format eprints
spelling my.um.eprints.259762021-05-25T03:02:09Z http://eprints.um.edu.my/25976/ A hybrid deep learning architecture for opinion-oriented multi-document summarization based on multi-feature fusion Abdi, Asad Hasan, Shafaatunnur Shamsuddin, Siti Mariyam Idris, Norisma Piran, Jalil QA75 Electronic computers. Computer science Opinion summarization is a process to produce concise summaries from a large number of opinionated texts. In this paper, we present a novel deep-learning-based method for the generic opinion-oriented extractive summarization of multi-documents (also known as RDLS). The method comprises sentiment analysis embedding space (SAS), text summarization embedding spaces (TSS) and opinion summarizer module (OSM). SAS employs recurrent neural network (RNN) which is composed by long short-term memory (LSTM) to take advantage of sequential processing and overcome several flaws in traditional methods, where order and information about a word have vanished. Furthermore, it uses sentiment knowledge, sentiment shifter rules and multiple strategies to overcome the existing drawbacks. TSS exploits multiple sources of statistical and linguistic knowledge features to augment word-level embedding and extract a proper set of sentences from multiple documents. TSS also uses the Restricted Boltzmann Machine algorithm to enhance and optimize those features and improve resultant accuracy without losing any important information. OSM consists of two phases: sentence classification and sentence selection which work together to produce a useful summary. Experiment results show that RDLS outperforms other existing methods. Moreover, the ensemble of statistical and linguistic knowledge, sentiment knowledge, sentiment shifter rules and word-embedding model allows RLDS to achieve significant accuracy. © 2020 Elsevier B.V. Elsevier 2021 Article PeerReviewed Abdi, Asad and Hasan, Shafaatunnur and Shamsuddin, Siti Mariyam and Idris, Norisma and Piran, Jalil (2021) A hybrid deep learning architecture for opinion-oriented multi-document summarization based on multi-feature fusion. Knowledge-Based Systems, 213. p. 106658. ISSN 0950-7051 https://doi.org/10.1016/j.knosys.2020.106658 doi:10.1016/j.knosys.2020.106658
institution Universiti Malaya
building UM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaya
content_source UM Research Repository
url_provider http://eprints.um.edu.my/
topic QA75 Electronic computers. Computer science
spellingShingle QA75 Electronic computers. Computer science
Abdi, Asad
Hasan, Shafaatunnur
Shamsuddin, Siti Mariyam
Idris, Norisma
Piran, Jalil
A hybrid deep learning architecture for opinion-oriented multi-document summarization based on multi-feature fusion
description Opinion summarization is a process to produce concise summaries from a large number of opinionated texts. In this paper, we present a novel deep-learning-based method for the generic opinion-oriented extractive summarization of multi-documents (also known as RDLS). The method comprises sentiment analysis embedding space (SAS), text summarization embedding spaces (TSS) and opinion summarizer module (OSM). SAS employs recurrent neural network (RNN) which is composed by long short-term memory (LSTM) to take advantage of sequential processing and overcome several flaws in traditional methods, where order and information about a word have vanished. Furthermore, it uses sentiment knowledge, sentiment shifter rules and multiple strategies to overcome the existing drawbacks. TSS exploits multiple sources of statistical and linguistic knowledge features to augment word-level embedding and extract a proper set of sentences from multiple documents. TSS also uses the Restricted Boltzmann Machine algorithm to enhance and optimize those features and improve resultant accuracy without losing any important information. OSM consists of two phases: sentence classification and sentence selection which work together to produce a useful summary. Experiment results show that RDLS outperforms other existing methods. Moreover, the ensemble of statistical and linguistic knowledge, sentiment knowledge, sentiment shifter rules and word-embedding model allows RLDS to achieve significant accuracy. © 2020 Elsevier B.V.
format Article
author Abdi, Asad
Hasan, Shafaatunnur
Shamsuddin, Siti Mariyam
Idris, Norisma
Piran, Jalil
author_facet Abdi, Asad
Hasan, Shafaatunnur
Shamsuddin, Siti Mariyam
Idris, Norisma
Piran, Jalil
author_sort Abdi, Asad
title A hybrid deep learning architecture for opinion-oriented multi-document summarization based on multi-feature fusion
title_short A hybrid deep learning architecture for opinion-oriented multi-document summarization based on multi-feature fusion
title_full A hybrid deep learning architecture for opinion-oriented multi-document summarization based on multi-feature fusion
title_fullStr A hybrid deep learning architecture for opinion-oriented multi-document summarization based on multi-feature fusion
title_full_unstemmed A hybrid deep learning architecture for opinion-oriented multi-document summarization based on multi-feature fusion
title_sort hybrid deep learning architecture for opinion-oriented multi-document summarization based on multi-feature fusion
publisher Elsevier
publishDate 2021
url http://eprints.um.edu.my/25976/
https://doi.org/10.1016/j.knosys.2020.106658
_version_ 1702170273141227520
score 13.209306