Sentiment analysis : an automatic contextual analysis and ensemble clustering approach and comparison

Product reviews are one of the most important resources to determine public sentiment. The existing literature on review sentiment analysis mostly utilizes supervised models, which usually suffer from domain-dependency and require expensive manual labelling effort to provide training data. This arti...

Full description

Saved in:
Bibliographic Details
Main Authors: AL-Sharuee, Murtadha Talib, Liu, Fei, Pratama, Mahardhika
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2020
Subjects:
Online Access:https://hdl.handle.net/10356/141504
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-141504
record_format dspace
spelling sg-ntu-dr.10356-1415042020-06-09T01:53:59Z Sentiment analysis : an automatic contextual analysis and ensemble clustering approach and comparison AL-Sharuee, Murtadha Talib Liu, Fei Pratama, Mahardhika School of Computer Science and Engineering Engineering::Computer science and engineering Text Mining Sentiment Analysis Product reviews are one of the most important resources to determine public sentiment. The existing literature on review sentiment analysis mostly utilizes supervised models, which usually suffer from domain-dependency and require expensive manual labelling effort to provide training data. This article addresses these issues by describing a completely automatic and unsupervised approach to sentiment analysis. The method consists of two phases, which are contextual analysis and unsupervised ensemble learning. In the implementation of both phases, a sentiment lexicon, SentiWordNet, is deployed. Using effective contextual procedures and modifying the base learning component (the k-means algorithm) results in developing a successful approach to sentiment analysis which can overcome the domain-dependency and the labelling cost problems. The results show that the proposed nonrandom initialization of k-means yields a significant improvement compared to other algorithms. In terms of accuracy and performance, the proposed method is effective compared to supervised and unsupervised approaches. We also introduce new sentiment analysis problems relating to Australian airlines and home builders which could be potential benchmark problems in the sentiment analysis field. Our experiments on datasets from different domains show that contextual analysis and the ensemble phases improve the clustering performance in term of accuracy, stability and generalizability. 2020-06-09T01:53:58Z 2020-06-09T01:53:58Z 2018 Journal Article AL-Sharuee, M. T., Liu, F., & Pratama, M. (2018). Sentiment analysis : an automatic contextual analysis and ensemble clustering approach and comparison. Data & Knowledge Engineering, 115, 194-213. doi:10.1016/j.datak.2018.04.001 0169-023X https://hdl.handle.net/10356/141504 10.1016/j.datak.2018.04.001 2-s2.0-85045340771 115 194 213 en Data & Knowledge Engineering © 2018 Elsevier B.V. All rights reserved.
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic Engineering::Computer science and engineering
Text Mining
Sentiment Analysis
spellingShingle Engineering::Computer science and engineering
Text Mining
Sentiment Analysis
AL-Sharuee, Murtadha Talib
Liu, Fei
Pratama, Mahardhika
Sentiment analysis : an automatic contextual analysis and ensemble clustering approach and comparison
description Product reviews are one of the most important resources to determine public sentiment. The existing literature on review sentiment analysis mostly utilizes supervised models, which usually suffer from domain-dependency and require expensive manual labelling effort to provide training data. This article addresses these issues by describing a completely automatic and unsupervised approach to sentiment analysis. The method consists of two phases, which are contextual analysis and unsupervised ensemble learning. In the implementation of both phases, a sentiment lexicon, SentiWordNet, is deployed. Using effective contextual procedures and modifying the base learning component (the k-means algorithm) results in developing a successful approach to sentiment analysis which can overcome the domain-dependency and the labelling cost problems. The results show that the proposed nonrandom initialization of k-means yields a significant improvement compared to other algorithms. In terms of accuracy and performance, the proposed method is effective compared to supervised and unsupervised approaches. We also introduce new sentiment analysis problems relating to Australian airlines and home builders which could be potential benchmark problems in the sentiment analysis field. Our experiments on datasets from different domains show that contextual analysis and the ensemble phases improve the clustering performance in term of accuracy, stability and generalizability.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
AL-Sharuee, Murtadha Talib
Liu, Fei
Pratama, Mahardhika
format Article
author AL-Sharuee, Murtadha Talib
Liu, Fei
Pratama, Mahardhika
author_sort AL-Sharuee, Murtadha Talib
title Sentiment analysis : an automatic contextual analysis and ensemble clustering approach and comparison
title_short Sentiment analysis : an automatic contextual analysis and ensemble clustering approach and comparison
title_full Sentiment analysis : an automatic contextual analysis and ensemble clustering approach and comparison
title_fullStr Sentiment analysis : an automatic contextual analysis and ensemble clustering approach and comparison
title_full_unstemmed Sentiment analysis : an automatic contextual analysis and ensemble clustering approach and comparison
title_sort sentiment analysis : an automatic contextual analysis and ensemble clustering approach and comparison
publishDate 2020
url https://hdl.handle.net/10356/141504
_version_ 1681056525865451520