Unfolding the characteristics of incentivized online reviews

Ana Costa, João Guerreiro, Sérgio Moro, Roberto Henriques

Research output: Contribution to journalArticle

Abstract

The rapid growth of social media in the last decades led e-commerce into a new era of value co-creation between the seller and the consumer. Since there is no contact with the product, people have to rely on the description of the seller, knowing that sometimes it may be biased and not entirely true. Therefore, review systems emerged to provide more trustworthy sources of information, since customer opinions may be less biased. However, the need to control the consumers’ opinion increased once sellers realized the importance of reviews and their direct impact on sales. One of the methods often used was to offer customers a specific product in exchange for an honest review. Yet, these incentivized reviews bias results and skew the overall rating of the products. The current study uses a data mining approach to predict whether or not a new review published was incentivized based on several review features such as the overall rating, the helpfulness rate, and the review length, among others. Additionally, the model was enriched with sentiment score features of the reviews computed through the VADER algorithm. The results provide an in-depth understanding of the phenomenon by identifying the most relevant features which enable to differentiate an incentivized from a non-incentivized review, thus providing users and companies with a simple set of rules to identify reviews that are biased without any disclaimer. Such rules include the length of a review, its helpfulness rate, and the overall sentiment polarity score.

LanguageEnglish
Pages272-281
Number of pages10
JournalJournal of Retailing and Consumer Services
Volume47
DOIs
Publication statusPublished - 1 Mar 2019

Fingerprint

Online reviews
Seller
Sentiment
Rating
Co-creation of value
Sources of information
Social media
Electronic commerce
Data mining

Keywords

  • Incentivized online reviews
  • Sentiment analysis
  • Text mining

Cite this

Costa, Ana ; Guerreiro, João ; Moro, Sérgio ; Henriques, Roberto. / Unfolding the characteristics of incentivized online reviews. In: Journal of Retailing and Consumer Services. 2019 ; Vol. 47. pp. 272-281.
@article{094453f9cba2468e8787b26d66a9e557,
title = "Unfolding the characteristics of incentivized online reviews",
abstract = "The rapid growth of social media in the last decades led e-commerce into a new era of value co-creation between the seller and the consumer. Since there is no contact with the product, people have to rely on the description of the seller, knowing that sometimes it may be biased and not entirely true. Therefore, review systems emerged to provide more trustworthy sources of information, since customer opinions may be less biased. However, the need to control the consumers’ opinion increased once sellers realized the importance of reviews and their direct impact on sales. One of the methods often used was to offer customers a specific product in exchange for an honest review. Yet, these incentivized reviews bias results and skew the overall rating of the products. The current study uses a data mining approach to predict whether or not a new review published was incentivized based on several review features such as the overall rating, the helpfulness rate, and the review length, among others. Additionally, the model was enriched with sentiment score features of the reviews computed through the VADER algorithm. The results provide an in-depth understanding of the phenomenon by identifying the most relevant features which enable to differentiate an incentivized from a non-incentivized review, thus providing users and companies with a simple set of rules to identify reviews that are biased without any disclaimer. Such rules include the length of a review, its helpfulness rate, and the overall sentiment polarity score.",
keywords = "Incentivized online reviews, Sentiment analysis, Text mining",
author = "Ana Costa and Jo{\~a}o Guerreiro and S{\'e}rgio Moro and Roberto Henriques",
note = "Costa, A., Guerreiro, J., Moro, S., & Henriques, R. (2019). Unfolding the characteristics of incentivized online reviews. Journal of Retailing and Consumer Services, 47, 272-281. DOI: 10.1016/j.jretconser.2018.12.006",
year = "2019",
month = "3",
day = "1",
doi = "10.1016/j.jretconser.2018.12.006",
language = "English",
volume = "47",
pages = "272--281",
journal = "Journal of Retailing and Consumer Services",
issn = "0969-6989",
publisher = "Elsevier",

}

Unfolding the characteristics of incentivized online reviews. / Costa, Ana; Guerreiro, João; Moro, Sérgio; Henriques, Roberto.

In: Journal of Retailing and Consumer Services, Vol. 47, 01.03.2019, p. 272-281.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Unfolding the characteristics of incentivized online reviews

AU - Costa, Ana

AU - Guerreiro, João

AU - Moro, Sérgio

AU - Henriques, Roberto

N1 - Costa, A., Guerreiro, J., Moro, S., & Henriques, R. (2019). Unfolding the characteristics of incentivized online reviews. Journal of Retailing and Consumer Services, 47, 272-281. DOI: 10.1016/j.jretconser.2018.12.006

PY - 2019/3/1

Y1 - 2019/3/1

N2 - The rapid growth of social media in the last decades led e-commerce into a new era of value co-creation between the seller and the consumer. Since there is no contact with the product, people have to rely on the description of the seller, knowing that sometimes it may be biased and not entirely true. Therefore, review systems emerged to provide more trustworthy sources of information, since customer opinions may be less biased. However, the need to control the consumers’ opinion increased once sellers realized the importance of reviews and their direct impact on sales. One of the methods often used was to offer customers a specific product in exchange for an honest review. Yet, these incentivized reviews bias results and skew the overall rating of the products. The current study uses a data mining approach to predict whether or not a new review published was incentivized based on several review features such as the overall rating, the helpfulness rate, and the review length, among others. Additionally, the model was enriched with sentiment score features of the reviews computed through the VADER algorithm. The results provide an in-depth understanding of the phenomenon by identifying the most relevant features which enable to differentiate an incentivized from a non-incentivized review, thus providing users and companies with a simple set of rules to identify reviews that are biased without any disclaimer. Such rules include the length of a review, its helpfulness rate, and the overall sentiment polarity score.

AB - The rapid growth of social media in the last decades led e-commerce into a new era of value co-creation between the seller and the consumer. Since there is no contact with the product, people have to rely on the description of the seller, knowing that sometimes it may be biased and not entirely true. Therefore, review systems emerged to provide more trustworthy sources of information, since customer opinions may be less biased. However, the need to control the consumers’ opinion increased once sellers realized the importance of reviews and their direct impact on sales. One of the methods often used was to offer customers a specific product in exchange for an honest review. Yet, these incentivized reviews bias results and skew the overall rating of the products. The current study uses a data mining approach to predict whether or not a new review published was incentivized based on several review features such as the overall rating, the helpfulness rate, and the review length, among others. Additionally, the model was enriched with sentiment score features of the reviews computed through the VADER algorithm. The results provide an in-depth understanding of the phenomenon by identifying the most relevant features which enable to differentiate an incentivized from a non-incentivized review, thus providing users and companies with a simple set of rules to identify reviews that are biased without any disclaimer. Such rules include the length of a review, its helpfulness rate, and the overall sentiment polarity score.

KW - Incentivized online reviews

KW - Sentiment analysis

KW - Text mining

UR - http://www.scopus.com/inward/record.url?scp=85058647683&partnerID=8YFLogxK

UR - http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS_CPL&DestLinkType=FullRecord&UT=WOS:000458215400030

U2 - 10.1016/j.jretconser.2018.12.006

DO - 10.1016/j.jretconser.2018.12.006

M3 - Article

VL - 47

SP - 272

EP - 281

JO - Journal of Retailing and Consumer Services

T2 - Journal of Retailing and Consumer Services

JF - Journal of Retailing and Consumer Services

SN - 0969-6989

ER -