Detecting deceptive reviews using lexical and syntactic features

Deceptive opinion classification has attracted a lot of research interest due to the rapid growth of social media users. Despite the availability of a vast number of opinion features and classification techniques, review classification still remains a challenging task. In this work we applied stylom...

Full description

Bibliographic Details
Main Authors: Shojaee, Somayeh, Azmi Murad, Masrah Azrifah, Azman, Azreen, Mohd Sharef, Nurfadhlina, Nadali, Samaneh
Format: Conference or Workshop Item
Published: IEEE (IEEEXplore) 2013
Online Access:http://psasir.upm.edu.my/id/eprint/41326/
_version_ 1848849665552809984
author Shojaee, Somayeh
Azmi Murad, Masrah Azrifah
Azman, Azreen
Mohd Sharef, Nurfadhlina
Nadali, Samaneh
author_facet Shojaee, Somayeh
Azmi Murad, Masrah Azrifah
Azman, Azreen
Mohd Sharef, Nurfadhlina
Nadali, Samaneh
author_sort Shojaee, Somayeh
building UPM Institutional Repository
collection Online Access
description Deceptive opinion classification has attracted a lot of research interest due to the rapid growth of social media users. Despite the availability of a vast number of opinion features and classification techniques, review classification still remains a challenging task. In this work we applied stylometric features, i.e. lexical and syntactic, using supervised machine learning classifiers, i.e. Support Vector Machine (SVM) with Sequential Minimal Optimization (SMO) and Naive Bayes, to detect deceptive opinion. Detecting deceptive opinion by a human reader is a difficult task because spammers try to write wise reviews, therefore it causes changes in writing style and verbal usage. Hence, considering the stylometric features help to distinguish the spammer writing style to find deceptive reviews. Experiments on an existing hotel review corpus suggest that using stylometric features is a promising approach for detecting deceptive opinions.
first_indexed 2025-11-15T09:54:00Z
format Conference or Workshop Item
id upm-41326
institution Universiti Putra Malaysia
institution_category Local University
last_indexed 2025-11-15T09:54:00Z
publishDate 2013
publisher IEEE (IEEEXplore)
recordtype eprints
repository_type Digital Repository
spelling upm-413262015-11-04T02:02:51Z http://psasir.upm.edu.my/id/eprint/41326/ Detecting deceptive reviews using lexical and syntactic features Shojaee, Somayeh Azmi Murad, Masrah Azrifah Azman, Azreen Mohd Sharef, Nurfadhlina Nadali, Samaneh Deceptive opinion classification has attracted a lot of research interest due to the rapid growth of social media users. Despite the availability of a vast number of opinion features and classification techniques, review classification still remains a challenging task. In this work we applied stylometric features, i.e. lexical and syntactic, using supervised machine learning classifiers, i.e. Support Vector Machine (SVM) with Sequential Minimal Optimization (SMO) and Naive Bayes, to detect deceptive opinion. Detecting deceptive opinion by a human reader is a difficult task because spammers try to write wise reviews, therefore it causes changes in writing style and verbal usage. Hence, considering the stylometric features help to distinguish the spammer writing style to find deceptive reviews. Experiments on an existing hotel review corpus suggest that using stylometric features is a promising approach for detecting deceptive opinions. IEEE (IEEEXplore) 2013 Conference or Workshop Item NonPeerReviewed Shojaee, Somayeh and Azmi Murad, Masrah Azrifah and Azman, Azreen and Mohd Sharef, Nurfadhlina and Nadali, Samaneh (2013) Detecting deceptive reviews using lexical and syntactic features. In: 2013 13th International Conference on Intelligent Systems Design and Applications (ISDA), 8-10 Dec. 2013, Bangi, Selangor, Malaysia. (pp. 53-58). 10.1109/ISDA.2013.6920707
spellingShingle Shojaee, Somayeh
Azmi Murad, Masrah Azrifah
Azman, Azreen
Mohd Sharef, Nurfadhlina
Nadali, Samaneh
Detecting deceptive reviews using lexical and syntactic features
title Detecting deceptive reviews using lexical and syntactic features
title_full Detecting deceptive reviews using lexical and syntactic features
title_fullStr Detecting deceptive reviews using lexical and syntactic features
title_full_unstemmed Detecting deceptive reviews using lexical and syntactic features
title_short Detecting deceptive reviews using lexical and syntactic features
title_sort detecting deceptive reviews using lexical and syntactic features
url http://psasir.upm.edu.my/id/eprint/41326/
http://psasir.upm.edu.my/id/eprint/41326/