Finding eWOM customers from customer reviews
| Published date | 04 February 2019 |
| Date | 04 February 2019 |
| DOI | https://doi.org/10.1108/IMDS-09-2017-0418 |
| Pages | 129-147 |
| Author | Pengfei Zhao,Ji Wu,Zhongsheng Hua,Shijian Fang |
| Subject Matter | Information & knowledge management,Information systems,Data management systems,Knowledge management,Knowledge sharing,Management science & operations,Supply chain management,Supply chain information systems,Logistics,Quality management/systems |
Finding eWOM customers from
customer reviews
Pengfei Zhao
School of Management, University of Science and Technology of China,
Hefei, China and
Department of Information Systems, City University of Hong Kong,
Kowloon, Hong Kong
Ji Wu
Business School, Sun Yat-sen University, Guangzhou, China
Zhongsheng Hua
School of Management, Zhejiang University, Hangzhou, China, and
Shijian Fang
University of Science and Technology of China, Hefei, China
Abstract
Purpose –The purpose of this paper is to identify electronic word-of-mouth (eWOM) customers from
customer reviews. Thus, firms can precisely leverage eWOM customers to increase their product sales.
Design/methodology/approach –This research proposed a framework to analyze the content of
consumer-generated product reviews. Specific algorithms were used to identify potential eWOM reviewers,
and then an evaluation method was used to validate the relationship between product sales and the eWOM
reviewers identified by the authors’proposed method.
Findings –The results corroborate that online product reviews that are made by the eWOM customers
identified by the authors’proposed method are more related to product sales than customer reviews that are
made by non-eWOM customers and that the predictive power of the reviews generated by eWOM customers
are significantly higher than the reviews generated by non-eWOM customers.
Research limitations/implications –The proposed method is useful in the data set, which is based on one
type of products. However, for other products, the validity must be tested. Previous eWOM customers may
have no significant influence on product sales in the future. Therefore, the proposed method should be tested
in the new market environment.
Practical implications –By combining the method with the previous customer segmentation method, a
new framework of customer segmentation is proposed to help firms understand customers’value specifically.
Originality/value –This study is the first to identify eWOM customers from online reviews and to evaluate
the relationship between reviewers and product sales.
Keywords Word-of-mouth, Sentiment analysis, Text mining, Online customer review, Product sales
Paper type Research paper
1. Introduction
Enabled by Web 2.0 technologies, social media provide an unparalleled platform for
consumers to share their product experiences and opinions through word-of-mouth (WOM).
With this platform, WOM is generated in unprecedented impacts on firm strategies and
consumer purchase behavior. Online customer reviews that act as a part of WOM marketing
(Duan et al., 2008) provide an alternative and effective marketing channel for firms to
advertise their products with low marketing costs. Previous studies affirmed that customer
reviews have impacts on product sales and that different features in customer reviews will
influence firms’product sales in different ways (Liu, 2006; Ghose and Ipeirotis, 2011;
Chevalier and Mayzlin, 2003). The literature confirms that some types of WOM information
tend to be more diagnostic than others (Herr et al., 1991; Mizerski, 1982). Industrial Management & Data
Systems
Vol. 119 No. 1, 2019
pp. 129-147
© Emerald PublishingLimited
0263-5577
DOI 10.1108/IMDS-09-2017-0418
Received 20 September 2017
Revised 7 March 2018
25 April 2018
Accepted 6 May 2018
The current issue and full text archive of this journal is available on Emerald Insight at:
www.emeraldinsight.com/0263-5577.htm
This work was supported by grants from the National Science Foundation of China (nos 71601190,
71771223, 71471157) and the Hong Kong GRF Grant No. 11504515.
129
Finding
eWOM
customers
From a firm’s perspective, providing customer reviews becomes an essential strategy to
improve product sales, and understanding online reviews and knowing how to influence
consumers’electronic word-of-mouth (eWOM) behavior is important for firms. Two
strategies that firms can use to influence the presentation of customer reviews are studied:
one is pricing, and the other is by finding and affecting customers (eWOM customers) who
are influential for firms’product sales by making reviews. For the price strategy, Xinxin Li
and Hitt (2010) validated that customer reviews can be influenced and biased by price
effects and that firms can set their price at a low level at the first stage to receive several
customer reviews and then increase it to maximize profit. However, studies on pricing
strategy for customer reviews are generally based on certain technical assumptions, but
empirical investigations are still needed to understand its implication for firm competition
(Chen and Xie, 2008). For the eWOM customer strategy, customers who make online product
reviews offer key information about product quality and, thus, can act as “information
assistants”for other customers’purchase decisions. The key to eWOM marketing is
customers/reviewers who spread product information to others (Li et al., 2010).
The openness and anonymity features resulted in a substantial increase in online reviews,
thereby giving information overload problems for customers and firms. Previous studies are
mainly from customers’perspectives and try to find reviewers who are reputable or helpful for
customers by studying their writing style in customer reviews (Li et al., 2010; Ku et al., 2012).
However, few studies focus on firms’needs. From firms’perspectives, they want to improve
their product sales by presenting good reviews. However, information or a review provided by
customers is a multi-attribute artifact and involves many features, such as ratings, sentiments,
readability and lexical style. Customers act in specific ways in these attributes; thus, their
reviews have different effects on helpfulness and product sales. Although the effects of different
attributes in customer reviews, such as rating, number of reviews, and readability on product
sales, are examined by many studies, all of these studies have to face serious challenges, that is,
reviews are unpredictable, and firms cannot take effective actions to influence the generation of
reviews and to increase firms’product sales (Ganu et al.,2013;Korfiatiset al., 2012). For these
problems to be addressed, only traditional methods can help firms filter some negative reviews
or put positive reviews in front when numerous reviews abound (Wang et al.,2016).This
method is passive and delayed. Although the effect of the review is unpredictable, but the
reviewers who write the reviews are more useful for firm marketing. The first reason is that the
number of reviewers is much smaller than the number of reviews. In addition, it is always
true that 20 percent reviewers seem to make the 80 percent reviews. The second reason is that
the reviewers are predictable and can be leveraged by firms in advance to generate the most
helpful reviews for product sales (Li et al., 2010; Ghose and Ipeirotis, 2011). However, a confusion
commonly happens here. Do the reviewers have the same effects on firms’product sales? Are
there customers who can have a big influence on firms’product sales by making online reviews?
How can firms identify customers who can help them improve their product sales by making
reviews? These questions are also important for customer classification.
To address these important research issues, we study customer reviewers from firms’
perspectives and design a method to identify the customers who are important for firms’
eWOM marketing from customer reviews. We distinguish customers based on their
influences on product sales by making customer reviews. Moreover, we define a new type of
customers, whom we call “eWOM customers,”as “customers who are helpful for firms’
product sales by providing online product reviews in social media.”To test the validity of
such a method from a marketer’s perspective, we conduct an empirical study based on
customer review data and sale data from an e-commerce company. Our results affirm a
strong linkage between our findings of eWOM customers and product sales.
The rest of this paper is organized as follows. Section 2 reviews the related literature.
Section 3 proposes a framework to identify eWOM customers from customer reviews.
130
IMDS
119,1
To continue reading
Request your trial