Cover Image

Machine learning-based multi-documents sentiment-oriented summarization using linguistic treatment

Sentiment summarization is the process of automatically creating a compressed version of the opinionated information expressed in a text. This paper presents a machine learning-based approach to summarize user's opinion expressed in reviews using: (1) Sentiment knowledge to calculate a sentence...

Full description

Saved in:
Bibliographic Details
Main Authors: Abdi, Asad, Shamsuddin, Siti Mariyam, Hasan, Shafaatunnur, MD. Jalil, Piran
Format: Article
Published: Elsevier Ltd 2018
Subjects:
Q Science (General)
Online Access:http://eprints.utm.my/id/eprint/84362/
http://dx.doi.org/10.1016/j.eswa.2018.05.010
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.84362
record_format eprints
spelling my.utm.843622019-12-28T01:48:45Z http://eprints.utm.my/id/eprint/84362/ Machine learning-based multi-documents sentiment-oriented summarization using linguistic treatment Abdi, Asad Shamsuddin, Siti Mariyam Hasan, Shafaatunnur MD. Jalil, Piran Q Science (General) Sentiment summarization is the process of automatically creating a compressed version of the opinionated information expressed in a text. This paper presents a machine learning-based approach to summarize user's opinion expressed in reviews using: (1) Sentiment knowledge to calculate a sentence sentiment score as one of the features for sentence-level classification. It integrates multiple strategies to tackle the following problems: sentiment shifter, the types of sentences and word coverage limit. (2) Word embedding model, a deep-learning-inspired method to understand meaning and semantic relationships among words and to extract a vector representation for each word. (3) Statistical and linguistic knowledge to determine salient sentences. The proposed method combines several types of features into a unified feature set to design a more accurate classification system (“True”: the extractive reference summary; “False”: otherwise). Thus, to achieve better performance scores, we carried out a performance study of four well-known feature selection techniques and seven of the most famous classifiers to select the most relevant set of features and find an efficient machine learning classifier, respectively. The proposed method is applied to three different datasets and the results show the integration of support vector machine-based classification method and Information Gain (IG) as a feature selection technique can significantly improve the performance and make the method comparable to other existing methods. Furthermore, our method that learns from this unified feature set can obtain better performance than one that learns from a feature subset. Elsevier Ltd 2018-11 Article PeerReviewed Abdi, Asad and Shamsuddin, Siti Mariyam and Hasan, Shafaatunnur and MD. Jalil, Piran (2018) Machine learning-based multi-documents sentiment-oriented summarization using linguistic treatment. Expert Systems with Applications, 109 . pp. 66-85. ISSN 0957-4174 http://dx.doi.org/10.1016/j.eswa.2018.05.010
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
topic Q Science (General)
spellingShingle Q Science (General)
Abdi, Asad
Shamsuddin, Siti Mariyam
Hasan, Shafaatunnur
MD. Jalil, Piran
Machine learning-based multi-documents sentiment-oriented summarization using linguistic treatment
description Sentiment summarization is the process of automatically creating a compressed version of the opinionated information expressed in a text. This paper presents a machine learning-based approach to summarize user's opinion expressed in reviews using: (1) Sentiment knowledge to calculate a sentence sentiment score as one of the features for sentence-level classification. It integrates multiple strategies to tackle the following problems: sentiment shifter, the types of sentences and word coverage limit. (2) Word embedding model, a deep-learning-inspired method to understand meaning and semantic relationships among words and to extract a vector representation for each word. (3) Statistical and linguistic knowledge to determine salient sentences. The proposed method combines several types of features into a unified feature set to design a more accurate classification system (“True”: the extractive reference summary; “False”: otherwise). Thus, to achieve better performance scores, we carried out a performance study of four well-known feature selection techniques and seven of the most famous classifiers to select the most relevant set of features and find an efficient machine learning classifier, respectively. The proposed method is applied to three different datasets and the results show the integration of support vector machine-based classification method and Information Gain (IG) as a feature selection technique can significantly improve the performance and make the method comparable to other existing methods. Furthermore, our method that learns from this unified feature set can obtain better performance than one that learns from a feature subset.
format Article
author Abdi, Asad
Shamsuddin, Siti Mariyam
Hasan, Shafaatunnur
MD. Jalil, Piran
author_facet Abdi, Asad
Shamsuddin, Siti Mariyam
Hasan, Shafaatunnur
MD. Jalil, Piran
author_sort Abdi, Asad
title Machine learning-based multi-documents sentiment-oriented summarization using linguistic treatment
title_short Machine learning-based multi-documents sentiment-oriented summarization using linguistic treatment
title_full Machine learning-based multi-documents sentiment-oriented summarization using linguistic treatment
title_fullStr Machine learning-based multi-documents sentiment-oriented summarization using linguistic treatment
title_full_unstemmed Machine learning-based multi-documents sentiment-oriented summarization using linguistic treatment
title_sort machine learning-based multi-documents sentiment-oriented summarization using linguistic treatment
publisher Elsevier Ltd
publishDate 2018
url http://eprints.utm.my/id/eprint/84362/
http://dx.doi.org/10.1016/j.eswa.2018.05.010
_version_ 1654960076825296896
score 13.211869

Similar Items