Data-Driven Customer Segmentation Based On Online Review Analysis and Customer Network Construction

2021 ◽  
Author(s):  
Seyoung Park ◽  
Harrison M. Kim
Keyword(s):  
Customer Segmentation ◽  
Market Analysis ◽  
Data Driven ◽  
Online Review ◽  
Online Data ◽  
Network Construction ◽  
Customer Reviews ◽  
Product Features ◽  
Review Analysis ◽  
Online Customer Reviews

Abstract Recently, many studies on product design have utilized online data for customer analysis. However, most of them treat online customers as a group of people with the same preferences while customer segmentation is a key strategy in conventional market analysis. To supplement this gap, this paper proposes a new methodology for online customer segmentation. First, customer attributes are extracted from online customer reviews. Then, a customer network is constructed based on the extracted attributes. Finally, the network is partitioned by modularity clustering and the resulting clusters are analyzed by topic frequency. The methodology is implemented to a smartphone review data. The result shows that online customers have different preferences as offline customers do, and they can be divided into separate groups with different tendencies for product features. This can help product designers to draw segment-based design implications from online data.

scholarly journals Online Review Solicitations Reduce Extremity Bias in Online Review Distributions and Increase Their Representativeness

2020 ◽  
Author(s):  
Hülya Karaman
Keyword(s):  
Past Research ◽  
Third Party ◽  
Online Review ◽  
Customer Reviews ◽  
Average Decrease ◽  
Online Word Of Mouth ◽  
Online Customer Reviews ◽  
Internet Economy ◽  
Online Ratings ◽  
Extreme Distribution

Representative online customer reviews are critical to the effective functioning of the Internet economy. In this study, I investigate the representativeness of online review distributions to examine how extremity bias and conformity impact it and explore whether online review solicitations alter representativeness. Past research on extreme distribution of online ratings commonly relied solely on observed public online ratings. One strength of the current paper is that I observe the private satisfaction ratings of customers regardless of whether they choose to write an online review or not. I show that both extremity bias and conformity exist in unsolicited online word-of-mouth (WOM) and introduce online review solicitations as a mechanism that can partially de-bias ratings. Solicitations increase all customers’ engagement in online WOM, but if solicited, those with moderate experiences increase their engagement more than those with extreme experiences. Consequently, although extremity bias still exists in solicited online WOM, solicitations significantly increase the representativeness of rating distributions. Surprisingly, the results demonstrate that without conformity, unsolicited online WOM would be even less representative of the original customer experiences. Furthermore, I document that both solicited and unsolicited reviews equally overstate the average customer experience (compared with average private ratings) despite stark differences in their rating distributions. Finally, I establish that solicitations for reviews on the company-owned website, on average, decrease the number of one-star reviews on a third-party review platform. This paper was accepted by Eric Anderson, marketing.

scholarly journals An Affordance-Based Online Review Analysis Framework

2019 ◽  
Vol 1 (1) ◽  
pp. 2457-2466
Author(s):  
Tianjun Hou ◽  
Bernard Yannou ◽  
Yann Leroy ◽  
Emilie Poirson
Keyword(s):  
Opinion Mining ◽  
Online Reviews ◽  
User Preferences ◽  
Data Driven ◽  
Online Review ◽  
Product Reviews ◽  
Analysis Framework ◽  
Review Analysis ◽  
Classical Models ◽  
Feedback Data

AbstractOne of the main tasks of today's data-driven design is to learn customers' concerns from the feedback data posted on the internet, to drive smarter and more profitable decisions during product development. Feature-based opinion mining was first performed by the computer and design scientists to analyse online product reviews. In order to provide more sophisticated customer feedback analyses and to understand in a deeper way customer concerns about products, the authors propose an affordance-based online review analysis framework. This framework allows understanding how and in what condition customers use their products, how user preferences change over years and how customers use the product innovatively. An empirical case study using the proposed approach is conducted with the online reviews of Kindle e-readers downloaded from amazon.com. A set of innovation leads and redesign paths are provided for the design of next-generation e-reader. This study suggests that bridging data analytics with classical models and methods in design engineering can bring success for data-driven design.

A Data-Driven Approach to Product Usage Context Identification From Online Customer Reviews

2019 ◽  
Vol 141 (12) ◽  
Author(s):  
Dedy Suryadi ◽  
Harrison M. Kim
Keyword(s):  
Sentiment Analysis ◽  
Language Processing ◽  
Consumer Satisfaction ◽  
Data Driven ◽  
Data Sets ◽  
Product Usage ◽  
Customer Reviews ◽  
Online Customer Reviews ◽  
Data Driven Approach ◽  
Usage Context

Abstract This paper proposes a data-driven methodology to automatically identify product usage contexts from online customer reviews. Product usage context is one of the factors that affect product design, consumer behavior, and consumer satisfaction. The previous works identify the usage contexts using the survey-based method or subjectively determine them. The proposed methodology, on the other hand, uses machine learning and Natural Language Processing tools to identify and cluster usage contexts from a large volume of customer reviews. Furthermore, aspect sentiment analysis is applied to capture the sentiment toward a particular usage context in a sentence. The methodology is implemented to two data sets of products, i.e., laptop and tablet. The result shows that the methodology is able to capture relevant product usage contexts and cluster bigrams that refer to similar usage context. The aspect sentiment analysis enables the observation of a product’s position with respect to its competitors for a particular usage context. For a product designer, the observation may indicate a requirement to improve the product. It may also indicate a possible market opportunity in a usage context in which most of the current products are perceived negatively by customers. Finally, it is shown that overall rating might not be a strong indicator for representing customer sentiment toward a particular usage context, due to the moderate linear correlation for most of the usage contexts in the case study.

Does the length of a review matter in perceived helpfulness? The moderating role of product experience

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Han Jia ◽  
Sumin Shin ◽  
Jinfeng Jiao
Keyword(s):  
Online Reviews ◽  
Product Type ◽  
Online Review ◽  
Content Type ◽  
Level Of Involvement ◽  
Customer Reviews ◽  
Product Experience ◽  
Online Customer Reviews ◽  
Review Helpfulness ◽  
Product Ratings

PurposeThis paper aims to offer a framework explaining how product experience (i.e. think vs feel) and product involvement (high vs low) influence the helpfulness of online reviews. It also reexamined how online consumer review dimensions help to build online review helpfulness under different contexts.Design/methodology/approachData were collected using content analysis on 1,200 online customer reviews on 12 products from four categories to measure the relationships between online review dimensions and the helpfulness of reviews. The regression analysis and analysis of variance (ANOVA) were used to test the hypotheses.FindingsThe findings indicate that the effectiveness of length of a review is moderated by product type; for think products, longer reviews yield higher helpfulness. Furthermore, the level of consistency between individual review ratings and overall product ratings is associated with review helpfulness. The length of product descriptions and product ratings is moderated by the level of involvement. For products with high involvement, longer descriptions yield higher helpfulness.Originality/valueA conceptual connection to customer interaction is proposed by online customer reviews that vary by product type. The findings provide implications for online retailers to better manage online customer reviews and increase the value of product ratings.

Mining opinionated product features using WordNet lexicographer files

2016 ◽  
Vol 43 (6) ◽  
pp. 769-785 ◽  
Author(s):  
Saif A. Ahmad Alrababah ◽  
Keng Hoon Gan ◽  
Tien-Ping Tan
Keyword(s):  
Assessment Tool ◽  
Empirical Evaluation ◽  
Online Reviews ◽  
Product Reviews ◽  
Specific Domain ◽  
Customer Reviews ◽  
Product Features ◽  
Online Customer Reviews ◽  
Customer Perspective ◽  
Massive Number

Online customer reviews are an important assessment tool for businesses as they contain feedback that is valuable from the customer perspective. These reviews provide a significant basis on which potential customers can select the product that best meets their preferences. In online reviews, customers describe positive or negative experiences with a product or service or any part of it (i.e. features). Consumers frequently experience difficulty finding the desired product for comparison because of the massive number of online reviews. The automatic extraction of important product features is necessary to support customers in search of relevant product features. These features are the criteria that make it possible for customers to characterise different types of products. This article proposes a domain independent approach for identifying explicit opinionated features and attributes that are strongly related to a specific domain product using lexicographer files in WordNet. In our approach, N_gram analysis and the SentiStrength opinion lexicon have been employed to support the extraction of opinionated features. The empirical evaluation of the proposed system using online reviews of two popular datasets of supervised and unsupervised systems showed that our approach achieved competitive results for feature extraction from product reviews.

Automated Mapping of Product Features Mined From Online Customer Reviews to Engineering Product Characteristics

2016 ◽  
Author(s):  
Sung woo Kang ◽  
Conrad S. Tucker
Keyword(s):  
New Product Development ◽  
Large Scale ◽  
Engineering Product ◽  
Automated Mapping ◽  
Customer Reviews ◽  
Pagerank Algorithm ◽  
Product Features ◽  
Online Customer Reviews ◽  
Scale Design

Until now, translating product features expressed in the market into quantifiable engineering metrics has primarily been a manual process. This manual process establishes product features from large-scale customer feedback using a product’s components from large-scale design specifications. This process exacerbates the complexity and sheer amount of information that designers must handle during the early stages of new product development. The methodology proposed in this paper automatically identifies product features by mapping terms that describe product features from technical descriptions and customer reviews. In order to discover terms related to the features expressed in the market, the authors of this work employ WordNet and the PageRank algorithm, which search for semantically similar terms in products’ technical descriptions. A case study demonstrates the methodology’s viability for matching product features that are extracted from online customer reviews to the technical descriptions that address them.

Predicting Future Importance of Product Features Based on Online Customer Reviews

2017 ◽  
Vol 139 (11) ◽  
Author(s):  
Huimin Jiang ◽  
C. K. Kwong ◽  
K. L. Yung
Keyword(s):  
Time Series ◽  
Opinion Mining ◽  
Fuzzy Inference ◽  
Online Reviews ◽  
Fuzzy Time Series ◽  
Series Method ◽  
Customer Reviews ◽  
Product Features ◽  
Online Customer Reviews ◽  
Time Series Method

Previous studies conducted customer surveys based on questionnaires and interviews, and the survey data were then utilized to analyze product features. In recent years, online customer reviews on products became extremely popular, which contain rich information on customer opinions and expectations. However, previous studies failed to properly address the determination of the importance of product features and prediction of their future importance based on online reviews. Accordingly, a methodology for predicting future importance weights of product features based on online customer reviews is proposed in this paper which mainly involves opinion mining, a fuzzy inference method, and a fuzzy time series method. Opinion mining is adopted to analyze the online reviews and extract product features. A fuzzy inference method is used to determine the importance weights of product features using both frequencies and sentiment scores obtained from opinion mining. A fuzzy time series method is adopted to predict the future importance of product features. A case study on electric irons was conducted to illustrate the proposed methodology. To evaluate the effectiveness of the fuzzy time series method in predicting the future importance, the results obtained by the fuzzy time series method are compared with those obtained by the three common forecasting methods. The results of the comparison show that the prediction results based on fuzzy time series method are better than those based on exponential smoothing, simple moving average, and fuzzy moving average methods.

scholarly journals ARTI PENTING TINGKAT KEPUASAN PARA PELANGGAN DAN PEMANFAATAN ULASAN DARING

2018 ◽  
Author(s):  
Dewanta Fachrureza
Keyword(s):  
Customer Satisfaction ◽  
Online Reviews ◽  
Online Review ◽  
Hotel Management ◽  
Customer Reviews ◽  
Online Customer Reviews ◽  
Front Office

<p>ABSTRACT</p><p>This research departs from the curiosity of researchers to find out the extent to which online customer reviews are used at the Ritz Carlton hotel, because hotel management responds well even to the extraordinary in responding to online customer reviews, especially from TripAdvisor. The purpose of this study is to develop and understand the extent to which online review customer reviews are used from TripAdvisor to the department of the front office at the Ritz Carlton Hotel Jakarta. Conclusions from this study are important for hotels to maintain and improve the level of customer satisfaction to improve the quality of hotel services. The researcher also gave several suggestions which stated that there must be a position of work that is responsible for ensuring that all online reviews will be answered and evaluated. In addition, the hotel must invite more guests to comment on TripAdvisor.<br />Keywords: Customer, Customer Satisfaction, Online Review, Front Office Department</p>

Study of E-Commerce Customer Review Capturing Process in the Indian Context

2022 ◽  
pp. 79-93
Author(s):  
Som Sekhar Bhattacharyya ◽  
Asmita Wani
Keyword(s):  
Research Work ◽  
Online Reviews ◽  
Point Of View ◽  
Online Review ◽  
Exploratory Research ◽  
Customer Reviews ◽  
Online Customer Reviews ◽  
Customer Review ◽  
Depth Interviews ◽  
Potential Customers

Online customer reviews provided by customers on e-commerce sites who had bought the products proved to be a key parameter. New and potential customers at the pre-purchase stage to vet the merits and demerits before buying new products listed on e-commerce sites referred to online customer reviews. However, there have been very few studies that focused on online customer review capturing process. Thus, this research work focused on the review capturing process of e-commerce websites from a customer's point of view to understand the online customer review process. A qualitative exploratory research was carried out. An open-ended semi-structured questionnaire was used to understand customer's stand on the e-commerce review capturing process. In-depth interviews were collected from customers. The data was analyzed thematic content. The study findings indicated what motivated customers to write online reviews, what inhibited them from writing reviews and what were their suggestions for the managers of e-commerce organizations towards designing better online review capturing.

A Systematic Methodology Based on Word Embedding for Identifying the Relation Between Online Customer Reviews and Sales Rank

2018 ◽  
Vol 140 (12) ◽  
Author(s):  
Dedy Suryadi ◽  
Harrison Kim
Keyword(s):  
Online Reviews ◽  
Word Embedding ◽  
Data Sets ◽  
Alternative Evaluation ◽  
Customer Reviews ◽  
Product Features ◽  
Online Customer Reviews ◽  
Dependency Tree ◽  
Systematic Methodology ◽  
Source Of Information

In the buying decision process, online reviews become an important source of information. They become the basis of evaluating alternatives before making purchase decision. This paper proposes a methodology to reveal one of the hidden alternative evaluation processes by identifying the relation between the observable online customer reviews and sales rank. This methodology applies a combined approach of word embedding (word2vec) and X-means clustering, which produces product-feature words. It is followed by identifying sentiment words and their intensity, determining connection of words from dependency tree, and finally relating variables from the reviews to the sales rank of a product by a regression model. The methodology is applied to two data sets of wearable technology and laptop products. As implied by the high predicted R-squared values, the models are generalizable into new data sets. Among the interesting findings are the statements of problems or issues of a product are related to better sales rank, and many product features that are mentioned in the review title are significantly related to sales rank. For product designers, the significant variables in the regression models suggest the possible product features to be improved.

Sign in / Sign up

Export Citation Format

Share Document