Detecting opinion spams through supervised boosting approach

Product reviews are the individual’s opinions, judgement or belief about a certain product or service provided by certain companies. Such reviews serve as guides for these companies to plan and monitor their business ventures in terms of increasing productivity or enhancing their product/service qua...

全面介绍

Saved in:
书目详细资料
Main Authors: Hazim, Mohamad, Anuar, Nor Badrul, Ab Razak, Mohd Faizal, Abdullah, Nor Aniza
格式: Article
出版: Public Library of Science 2018
主题:
在线阅读:http://eprints.um.edu.my/21909/
https://doi.org/10.1371/journal.pone.0198884
标签: 添加标签
没有标签, 成为第一个标记此记录!
id my.um.eprints.21909
record_format eprints
spelling my.um.eprints.219092019-08-08T06:37:25Z http://eprints.um.edu.my/21909/ Detecting opinion spams through supervised boosting approach Hazim, Mohamad Anuar, Nor Badrul Ab Razak, Mohd Faizal Abdullah, Nor Aniza QA75 Electronic computers. Computer science QA76 Computer software Product reviews are the individual’s opinions, judgement or belief about a certain product or service provided by certain companies. Such reviews serve as guides for these companies to plan and monitor their business ventures in terms of increasing productivity or enhancing their product/service qualities. Product reviews can also increase business profits by convincing future customers about the products which they have interest in. In the mobile application marketplace such as Google Playstore, reviews and star ratings are used as indicators of the application quality. However, among all these reviews, hereby also known as opinions, spams also exist, to disrupt the online business balance. Previous studies used the time series and neural network approach (which require a lot of computational power) to detect these opinion spams. However, the detection performance can be restricted in terms of accuracy because the approach focusses on basic, discrete and document level features only thereby, projecting little statistical relationships. Aiming to improve the detection of opinion spams in mobile application marketplace, this study proposes using statistical based features that are modelled through the supervised boosting approach such as the Extreme Gradient Boost (XGBoost) and the Generalized Boosted Regression Model (GBM) to evaluate two multilingual datasets (i.e. English and Malay language). From the evaluation done, it was found that the XGBoost is most suitable for detecting opinion spams in the English dataset while the GBM Gaussian is most suitable for the Malay dataset. The comparative analysis also indicates that the implementation of the proposed statistical based features had achieved a detection accuracy rate of 87.43 per cent on the English dataset and 86.13 per cent on the Malay dataset. Public Library of Science 2018 Article PeerReviewed Hazim, Mohamad and Anuar, Nor Badrul and Ab Razak, Mohd Faizal and Abdullah, Nor Aniza (2018) Detecting opinion spams through supervised boosting approach. PLoS ONE, 13 (6). e0198884. ISSN 1932-6203 https://doi.org/10.1371/journal.pone.0198884 doi:10.1371/journal.pone.0198884
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
QA76 Computer software
spellingShingle QA75 Electronic computers. Computer science
QA76 Computer software
Hazim, Mohamad
Anuar, Nor Badrul
Ab Razak, Mohd Faizal
Abdullah, Nor Aniza
Detecting opinion spams through supervised boosting approach
description Product reviews are the individual’s opinions, judgement or belief about a certain product or service provided by certain companies. Such reviews serve as guides for these companies to plan and monitor their business ventures in terms of increasing productivity or enhancing their product/service qualities. Product reviews can also increase business profits by convincing future customers about the products which they have interest in. In the mobile application marketplace such as Google Playstore, reviews and star ratings are used as indicators of the application quality. However, among all these reviews, hereby also known as opinions, spams also exist, to disrupt the online business balance. Previous studies used the time series and neural network approach (which require a lot of computational power) to detect these opinion spams. However, the detection performance can be restricted in terms of accuracy because the approach focusses on basic, discrete and document level features only thereby, projecting little statistical relationships. Aiming to improve the detection of opinion spams in mobile application marketplace, this study proposes using statistical based features that are modelled through the supervised boosting approach such as the Extreme Gradient Boost (XGBoost) and the Generalized Boosted Regression Model (GBM) to evaluate two multilingual datasets (i.e. English and Malay language). From the evaluation done, it was found that the XGBoost is most suitable for detecting opinion spams in the English dataset while the GBM Gaussian is most suitable for the Malay dataset. The comparative analysis also indicates that the implementation of the proposed statistical based features had achieved a detection accuracy rate of 87.43 per cent on the English dataset and 86.13 per cent on the Malay dataset.
format Article
author Hazim, Mohamad
Anuar, Nor Badrul
Ab Razak, Mohd Faizal
Abdullah, Nor Aniza
author_facet Hazim, Mohamad
Anuar, Nor Badrul
Ab Razak, Mohd Faizal
Abdullah, Nor Aniza
author_sort Hazim, Mohamad
title Detecting opinion spams through supervised boosting approach
title_short Detecting opinion spams through supervised boosting approach
title_full Detecting opinion spams through supervised boosting approach
title_fullStr Detecting opinion spams through supervised boosting approach
title_full_unstemmed Detecting opinion spams through supervised boosting approach
title_sort detecting opinion spams through supervised boosting approach
publisher Public Library of Science
publishDate 2018
url http://eprints.um.edu.my/21909/
https://doi.org/10.1371/journal.pone.0198884
_version_ 1643691695818145792
score 13.154949