Let's vote to classify authentic and manipulative online reviews: The role of comprehensibility, informativeness and writing style

Snehasish Banerjee; Alton Y.K. Chua; Jung Jae Kim

doi:10.1109/SAI.2015.7237129

Let's vote to classify authentic and manipulative online reviews: The role of comprehensibility, informativeness and writing style

Snehasish Banerjee, Alton Y.K. Chua, Jung Jae Kim

Nanyang Technological University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Citations (Scopus)

Abstract

Scholars increasingly seek to investigate differences between authentic and manipulative online reviews. A common line of research argues that authentic and manipulative reviews are distinguishable based on three textual characteristics, namely, comprehensibility, informativeness and writing style. Although recent studies have analyzed differences between authentic and manipulative reviews in terms of these textual characteristics, they often lack in terms of methodological rigor. For one, datasets used for analysis are not always representative. Moreover, only few machine learning algorithms are used to classify authentic and manipulative reviews. Recognizing the value of methodological rigor, this paper extends prior studies by examining textual differences between authentic and manipulative reviews using a more representative dataset. Moreover, authentic and manipulative reviews were classified using a voting among multiple classifiers that had been used in recent literature. The implications of the results are discussed.

Original language	English
Title of host publication	Proceedings of the 2015 Science and Information Conference, SAI 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	77-83
Number of pages	7
ISBN (Electronic)	9781479985470
DOIs	https://doi.org/10.1109/SAI.2015.7237129
Publication status	Published - Sept 2 2015
Externally published	Yes
Event	Science and Information Conference, SAI 2015 - London, United Kingdom Duration: Jul 28 2015 → Jul 30 2015

Publication series

Name	Proceedings of the 2015 Science and Information Conference, SAI 2015

Conference

Conference	Science and Information Conference, SAI 2015
Country/Territory	United Kingdom
City	London
Period	7/28/15 → 7/30/15

Bibliographical note

Publisher Copyright:
© 2015 IEEE.

ASJC Scopus Subject Areas

Health Informatics
Social Sciences (miscellaneous)
Computer Science Applications
Human-Computer Interaction
Computer Networks and Communications
Information Systems
Software

Keywords

authentic
classification
comprehensibility
informativeness
manipulative
online reviews
voting
writing style

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/SAI.2015.7237129

Cite this

Banerjee, S., Chua, A. Y. K., & Kim, J. J. (2015). Let's vote to classify authentic and manipulative online reviews: The role of comprehensibility, informativeness and writing style. In Proceedings of the 2015 Science and Information Conference, SAI 2015 (pp. 77-83). Article 7237129 (Proceedings of the 2015 Science and Information Conference, SAI 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SAI.2015.7237129

Banerjee, Snehasish ; Chua, Alton Y.K. ; Kim, Jung Jae. / Let's vote to classify authentic and manipulative online reviews : The role of comprehensibility, informativeness and writing style. Proceedings of the 2015 Science and Information Conference, SAI 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 77-83 (Proceedings of the 2015 Science and Information Conference, SAI 2015).

@inproceedings{faf04a124268462fbc7611c2b8b0061e,

title = "Let's vote to classify authentic and manipulative online reviews: The role of comprehensibility, informativeness and writing style",

abstract = "Scholars increasingly seek to investigate differences between authentic and manipulative online reviews. A common line of research argues that authentic and manipulative reviews are distinguishable based on three textual characteristics, namely, comprehensibility, informativeness and writing style. Although recent studies have analyzed differences between authentic and manipulative reviews in terms of these textual characteristics, they often lack in terms of methodological rigor. For one, datasets used for analysis are not always representative. Moreover, only few machine learning algorithms are used to classify authentic and manipulative reviews. Recognizing the value of methodological rigor, this paper extends prior studies by examining textual differences between authentic and manipulative reviews using a more representative dataset. Moreover, authentic and manipulative reviews were classified using a voting among multiple classifiers that had been used in recent literature. The implications of the results are discussed.",

keywords = "authentic, classification, comprehensibility, informativeness, manipulative, online reviews, voting, writing style",

author = "Snehasish Banerjee and Chua, {Alton Y.K.} and Kim, {Jung Jae}",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; Science and Information Conference, SAI 2015 ; Conference date: 28-07-2015 Through 30-07-2015",

year = "2015",

month = sep,

day = "2",

doi = "10.1109/SAI.2015.7237129",

language = "English",

series = "Proceedings of the 2015 Science and Information Conference, SAI 2015",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "77--83",

booktitle = "Proceedings of the 2015 Science and Information Conference, SAI 2015",

address = "United States",

}

Banerjee, S, Chua, AYK & Kim, JJ 2015, Let's vote to classify authentic and manipulative online reviews: The role of comprehensibility, informativeness and writing style. in Proceedings of the 2015 Science and Information Conference, SAI 2015., 7237129, Proceedings of the 2015 Science and Information Conference, SAI 2015, Institute of Electrical and Electronics Engineers Inc., pp. 77-83, Science and Information Conference, SAI 2015, London, United Kingdom, 7/28/15. https://doi.org/10.1109/SAI.2015.7237129

Let's vote to classify authentic and manipulative online reviews: The role of comprehensibility, informativeness and writing style. / Banerjee, Snehasish; Chua, Alton Y.K.; Kim, Jung Jae.
Proceedings of the 2015 Science and Information Conference, SAI 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 77-83 7237129 (Proceedings of the 2015 Science and Information Conference, SAI 2015).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Let's vote to classify authentic and manipulative online reviews

T2 - Science and Information Conference, SAI 2015

AU - Banerjee, Snehasish

AU - Chua, Alton Y.K.

AU - Kim, Jung Jae

PY - 2015/9/2

Y1 - 2015/9/2

N2 - Scholars increasingly seek to investigate differences between authentic and manipulative online reviews. A common line of research argues that authentic and manipulative reviews are distinguishable based on three textual characteristics, namely, comprehensibility, informativeness and writing style. Although recent studies have analyzed differences between authentic and manipulative reviews in terms of these textual characteristics, they often lack in terms of methodological rigor. For one, datasets used for analysis are not always representative. Moreover, only few machine learning algorithms are used to classify authentic and manipulative reviews. Recognizing the value of methodological rigor, this paper extends prior studies by examining textual differences between authentic and manipulative reviews using a more representative dataset. Moreover, authentic and manipulative reviews were classified using a voting among multiple classifiers that had been used in recent literature. The implications of the results are discussed.

AB - Scholars increasingly seek to investigate differences between authentic and manipulative online reviews. A common line of research argues that authentic and manipulative reviews are distinguishable based on three textual characteristics, namely, comprehensibility, informativeness and writing style. Although recent studies have analyzed differences between authentic and manipulative reviews in terms of these textual characteristics, they often lack in terms of methodological rigor. For one, datasets used for analysis are not always representative. Moreover, only few machine learning algorithms are used to classify authentic and manipulative reviews. Recognizing the value of methodological rigor, this paper extends prior studies by examining textual differences between authentic and manipulative reviews using a more representative dataset. Moreover, authentic and manipulative reviews were classified using a voting among multiple classifiers that had been used in recent literature. The implications of the results are discussed.

KW - authentic

KW - classification

KW - comprehensibility

KW - informativeness

KW - manipulative

KW - online reviews

KW - voting

KW - writing style

UR - http://www.scopus.com/inward/record.url?scp=84957803622&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84957803622&partnerID=8YFLogxK

U2 - 10.1109/SAI.2015.7237129

DO - 10.1109/SAI.2015.7237129

M3 - Conference contribution

AN - SCOPUS:84957803622

T3 - Proceedings of the 2015 Science and Information Conference, SAI 2015

SP - 77

EP - 83

BT - Proceedings of the 2015 Science and Information Conference, SAI 2015

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 28 July 2015 through 30 July 2015

ER -

Banerjee S, Chua AYK, Kim JJ. Let's vote to classify authentic and manipulative online reviews: The role of comprehensibility, informativeness and writing style. In Proceedings of the 2015 Science and Information Conference, SAI 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 77-83. 7237129. (Proceedings of the 2015 Science and Information Conference, SAI 2015). doi: 10.1109/SAI.2015.7237129

Let's vote to classify authentic and manipulative online reviews: The role of comprehensibility, informativeness and writing style

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus Subject Areas

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this