Online Product Reviews Research Articles

Antecedents of consumers’ reliance on online product reviews

PurposeThis paper examines the role that attitudes toward online product reviews (OPRs), perceived credibility of OPRs and perceived benefit of OPRs play as antecedents of consumers’ reliance on OPRs in purchase decisions. A conceptual model of relationships investigated posits that attitudes drive reliance and are in turn driven by perceived benefit and credibility of OPRs. The study also examines gender differences in the constructs and their inter-relationships.Design/methodology/approachData from a structured self-administered survey of US consumers are used to estimate parameters of a structural equation model (SEM) of the relationships. Gender differences in the structural relationships are tested using multi-group SEM, while gender differences in reliance, attitudes, benefit and credibility are tested using independent-samples t-tests.FindingsResults show a strong positive effect of attitudes toward OPRs on reliance on OPRs. In turn, perceived benefit and credibility of OPRs are strong positive drivers of attitudes toward OPRs, with benefit having a greater impact. Structural relationships among the constructs are invariant across the two gender groups. However, there is a statistically significant difference between males and females in reliance on OPRs, with males exhibiting a tendency to rely more on OPRs than females.Originality/valueThe study introduces two new constructs to the literature – reliance on OPRs and global attitudes toward OPRs – and provides initial conceptualizations and operationalizations. The specific results underscore the relevance and importance of further research on these constructs and their relationships with other OPR-relevant constructs. They also provide initial indications of gender differences in consumers’ perceptions of OPRs and relationships among these and reliance on OPRs that are worthy of additional research attention.

Determining the semantic orientation of opinion words using typed dependencies for opinion word senses and SentiWordNet scores from online product reviews

Determining the semantic orientation of opinion words using typed dependencies for opinion word senses and SentiWordNet scores from online product reviews

Challenges and Recommended Solutions in Multi-Source and Multi-Domain Sentiment Analysis

The massive availability of online reviews and postings in social media offers invaluable feedback for businesses to make better informed decisions in steering their marketing strategies towards users' interests and preferences. Sentiment analysis is, therefore, essential for determining the public's opinion towards a particular topic, product or service. Traditionally, sentiment analysis is performed on a single data source, for instance, online product reviews or Tweets. However, the need to develop a more precise, and more comprehensive result has steered the move towards performing sentiment analysis on multiple data sources. The use of multiple data sources for a particular domain of interest can increase the amount of datasets needed for training a sentiment classifier. Till now, the problem of insufficient datasets for training the classifier is only addressed by multi-domain sentiment analysis. Aiming to equip researchers with a thorough understanding on both multi-source and multi-domain sentiment analysis, this paper aims to identify the underlying challenges of multi-source and multi-domain sentiment analysis, and discuss the solutions applied by the researchers concerned. This paper also offers an insightful discussion of the findings derived from past studies, and based on these, propose some useful suggestions for the future direction of this research area. Findings derived from our review would be beneficial towards guiding researchers towards the future progress and advancement of multi-source and multi-domain sentiment analysis.

Detecting fake reviews via dynamic multimode network

Online product reviews can greatly affect the consumer's shopping decision. Thus, a larger number of unscrupulous merchants post fake or unfair reviews to mislead consumers for their profit and fame. The common approaches to find these spam reviews are analysing the text similarity or rating pattern. With these common approaches we can easily identify ordinary spammers, but we cannot find the unusual ones who manipulate their behaviour to act just like genuine reviewers. In this paper, we propose a novel method to recognise these unusual ones by using relations among reviewers, reviews, commodities and stores. Firstly, we present four fundamental concepts, which are the quality of the merchandise, the honesty of the review, the trustworthiness of the reviewer and the reliability of the store, thus enabling us to identify the spam reviewers more efficiently. Secondly, we propose our multimode network model for identifying suspicious reviews and then give three corresponding algorithms. Eventually, we find that the multi-view spam detection based on the multimode network can detect more subtle false reviews according to our experiments.

The effects of extrinsic cues on online sales of fresh produce: a focus on geographical indications

Fresh produce has rich sensory attributes, and consumers generally prefer examining physically these sensory attributes prior to purchase. The nature of e-commerce, however, limits consumers’ ability to examine products’ sensory attributes while buying online. Customers receive very limited intrinsic cues of fresh produce (such as color) when buying online and thus use only extrinsic cues to assess the quality of fresh produce. This study investigates the effects of extrinsic cues on online shopping for fresh produce, with a particular focus on the effect of geographical indication (GI), which often assumes the role of brand names among producers of fresh groceries. We used data from an online South Korean marketplace for fresh produce to conduct a linear regression analysis. The results show that products linked to GIs sold more and were ordered more frequently; other control variables had somewhat significant effects. The volume of online product reviews was found to have a significant positive effect on the amount of orders and sales, but the product rating itself did not have an effect. The price had a negative effect on the amount of orders, while the number of certifications (e.g. “organic agriculture”) had a significant positive effect on the number of orders.

Detecting fake reviews via dynamic multimode network

Online product reviews can greatly affect the consumer's shopping decision. Thus, a larger number of unscrupulous merchants post fake or unfair reviews to mislead consumers for their profit and fame. The common approaches to find these spam reviews are analysing the text similarity or rating pattern. With these common approaches we can easily identify ordinary spammers, but we cannot find the unusual ones who manipulate their behaviour to act just like genuine reviewers. In this paper, we propose a novel method to recognise these unusual ones by using relations among reviewers, reviews, commodities and stores. Firstly, we present four fundamental concepts, which are the quality of the merchandise, the honesty of the review, the trustworthiness of the reviewer and the reliability of the store, thus enabling us to identify the spam reviewers more efficiently. Secondly, we propose our multimode network model for identifying suspicious reviews and then give three corresponding algorithms. Eventually, we find that the multi-view spam detection based on the multimode network can detect more subtle false reviews according to our experiments.

Is More Better? Divide between Retailer's and Manufacturers' Preferences for Reviews and Review Monetization

Research on online product reviews has examined a variety of issues ranging from reviewers' motivation to write reviews to impact of reviews on product sales. Implicit in a large number of studies in this research stream is the notion that more reviews is better for sellers and consumers. However, it is unclear whether a retailer, who often controls the review platform, and manufacturers, whose products are being reviewed, prefer more reviews to less. Using a game theoretical model of a context in which a retailer sells competing products from two manufacturers and consumers are uncertain about product qualities, we show that the retailer's and the manufacturers' preferences regarding the number of reviews are not always aligned. If the reviews are costless, then additional reviews benefit the retailer, but manufacturers are hurt by additional reviews when the number of reviews exceeds a threshold. Moreover, if the consumers' own uncertainty about product qualities is not too high, then the manufacturers do not prefer to have reviews at all. On the other hand, if the retailer incurs a sufficiently high cost to generate reviews, he may prefer to have fewer reviews than manufacturers. We show that the divide between the retailer's and the manufacturers' preferences can induce the retailer to monetize reviews by charging a fee to manufacturers in return for a guarantee on the number of reviews that would be made available in the review platform. The retailer's revenue from such monetization follows a U-shape with respect to the cost of generating reviews as well as the extent to which reviews can reveal true product quality, suggesting that the product type and review platform design play a significant role in the attractiveness of review monetization for the retailer. The revenue from reviews to manufacturers does not exceed the cost of generating reviews, implying the retailer's benefit from reviews, even when they can be monetized, is driven by reviews' positive impacts on the retailer's core business of selling products to consumers. The findings provide economic insights into the nascent efforts of Amazon to monetize reviews through programs such as Amazon Vine.

Integrating Topic, Sentiment, and Syntax for Modeling Online Reviews: A Topic Model Approach

Analyzing product online reviews has drawn much interest in the academic field. In this research, a new probabilistic topic model, called tag sentiment aspect models (TSA), is proposed on the basis of Latent Dirichlet allocation (LDA), which aims to reveal latent aspects and corresponding sentiment in a review simultaneously. Unlike other topic models which consider words in online reviews only, syntax tags are taken as visual information and, in this research, as a kind of widely used syntax information, part-of-speech (POS) tags are first reckoned. Specifically, POS tags are integrated into three versions of implementation in consideration of the fact that words with different POS tags might be utilized to express consumers' opinions. Also, the proposed TSA is one unsupervised approach and only a small number of positive and negative words are required to confine different priors for training. Finally, two big datasets regarding digital SLR and laptop are utilized to evaluate the performance of the proposed model in terms of sentiment classification and aspect extraction. Comparative experiments show that the new model can not only achieve promising results on sentiment classification but also leverage the performance on aspect extraction.

Utilizing text mining and Kansei Engineering to support data-driven design automation at conceptual design stage

PurposeThe purpose of this research was to develop a case-based method for analyzing online customer reviews and extracting customer preferences through an integration of text mining and Kansei Engineering (KE) in an effort to achieve conceptual data-driven design automation and to successfully identify future trends in a particular consumer product.Design/Methodology/Approach This study’s model merges text mining and KE to extract key descriptive Kansei terminology according to actual customer reviews and use it to forecast consumer preferred product design while reducing certain repetitious tasks of designers. This work first collects online product reviews using text mining. Then, through the application of KE, the customer-preferred design components are identified and incorporated into the product design specifications. Finally, an Application Programming Interface (API) is developed to automatically generate a CAD preliminary design.Case Study A road bike case study is provided to demonstrate the practicality of proposed method. The online reviews are collected from Amazon.com. The related design elements are classified into six key components which can be modified in the proposed conceptual design automation system.Originality/value This is the first paper that has applied text mining and KE for use in product development. This work can also reduce the time and cost of product design through the automation of repetitive design tasks. The conceptual design automation system is valuable for designers wishing to identify customer needs and to generate engineering drawings in a timely manner without significant repetition during the design process.

A Semi-supervised Approach for Opinion Mining using Online Product Review

The growth of the internet as a secure online shopping channel has developed since 1994. With the Increasing number of e-commerce portal, we are now heavily inclined to online shopping. One of the benefits of online shopping is the ability to read reviews about the product purchased. This paper presents a semi-supervised approach for opinion mining using online product reviews obtained from Amazon website. A semi-supervised model regards identifying opinion relation as an alignment process and gives more precision in comparison to unsupervised model. Opinion mining of online reviews is needed for first-hand assessments of product information and direct supervision of their purchase actions. Manufacturers can obtain immediate feedback and opportunities to improve the quality of their products in a timely fashion.

Sentiment Mining of Online Product Reviews Based on Domain Ontology

Sentiment Mining of Online Product Reviews Based on Domain Ontology

Finding eWOM customers from customer reviews

PurposeThe 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/approachThis 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.FindingsThe 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/implicationsThe 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 implicationsBy 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/valueThis study is the first to identify eWOM customers from online reviews and to evaluate the relationship between reviewers and product sales.

An Approach for Detecting Polarity of Online Product Reviews Based on Opinion Target and Opinion Words from Reviews

An Approach for Detecting Polarity of Online Product Reviews Based on Opinion Target and Opinion Words from Reviews

E-tailer website attributes and trust: understanding the role of online reviews

PurposeThe purpose of this paper is to report the results of an experimental study designed to better understand the role of online product reviews, both valence and volume, in the formation of initial online trust during a consumer’s exploratory stage with an e-tailer. This is done within the context of simultaneously varying e-tailer reputation and product type.Design/methodology/approachParticipants take part in a conjoint task that involves viewing fictitious web pages and indicating their level of trust in using the site to purchase the product displayed. The web pages are developed by manipulating four attributes (e-tailer reputation, product type, summary product star rating and number of online reviews) according to a full factorial design. Conjoint models are estimated to determine the relative influence of each attribute on trust perceptions, the significance of selected two-way interactions among the four attributes, and potential moderating effects of varied prior online experiences, including previous usage frequency of online reviews.FindingsResults reveal that e-tailer reputation has the greatest impact on initial trust perceptions, followed by the summary review star rating of the product. Significant two-way interactions show that a large number of reviews enhance the effect of a positive summary review on trust while shopping for high priced experience products diminishes the positive influence of e-tailer reputation. Prior online experiences moderate the relationship between these website attributes and perceived trust by interacting with the two strongest trust cues in the model. The effects of these attributes on trust perceptions are less for those with higher levels of prior online experiences.Originality/valueThe study uses conjoint analysis, which requires participants to implicitly “tradeoff” among website attributes in making overall judgments about e-tailer trustworthiness. Consequently, the relative influence of online reviews (both valence and volume) on initial trust perceptions is derived empirically in a realistic setting that involves online shopping contexts with different risk (by varying product type). Moreover, the authors are able to estimate interaction effects. A significant interaction between summary product star rating and number of reviews implies that online review volume may be more important to perceived e-tailer trustworthiness than earlier studies suggest.

Application of data analytics for product design: Sentiment analysis of online product reviews

Advanced data analytics is one of the most revolutionary technological developments in the 21st century, which enables the discovery of underlining trends via sophisticated computational methods On various e-commerce and social platforms, millions of online product reviews are published by customers, which can potentially provide designers with invaluable insights into product design. This paper presents a design framework to analyze online product reviews. The objective is to use this machine-generated data to identify a series of customer needs. The framework aims to distill large volumes of qualitative data into quantitative insights on product features, so that designers can make more informed decisions. The framework combines the elements of online product reviews, design theory and methodology, and data analytics to reveal new insights. The effectiveness of the proposal framework is validated through a case study on product reviews from the e-commerce website, Amazon. The framework demonstrates a statistical approach for analyzing online product reviews. The framework acts as an interface between quantitative outputs and the qualitative and creative process of design. Further analysis of results identifies many of incorporating logical, computational methods into the highly subjective and creative process of design.

A Unique Method of Constructing Brand Perceptual Maps by the Text Mining of Multimedia Consumer Reviews

Brand perceptual mapping is a visual technique, it displays how a brand is positioned in the mind of customers, as well as in relation to the competitors. With the rapid growth of e-commerce and the abundance of online consumer-generated content, there is no need for marketers to go through market research in order to understand consumers' opinions. Therefore, in this study, the authors propose a unique method which allows the building of a perceptual map automatically by mining consumer opinions from in particular online product reviews. The authors employ opinion mining techniques to extract and rank the product aspects that are important to customers, during purchasing digital tablets. Subsequently, they generate a score for each brand in these aspects and build the perceptual map using clustering of the brands by these scores. This proposed method is applied to the online customer reviews for digital tablets obtained from Amazon.com. The experimental results highlight the proposed technique is effective and able to correctly depict the position of a brand in its particular competitive environment.

Credibility Analysis for Online Product Reviews

With the prevalence of e-commerce, online product reviews are increasingly considered crowd-sourced consumer opinions that significantly influence customer purchasing decisions and product rankings. It is therefore important to ensure the truthfulness of reviews by detecting and filtering out fake/spam reviews. This article presents an effective framework to analyze review credibility for spam detection and opinion mining. It incorporates three methods: duplicated review detection, anomaly detection, and incentivized review detection, that complement each other to produce statistical credibility scores indicating review credibility. A practical end-to-end system is designed and developed accordingly, and is equipped with high-level data visualization for easy interpretation and summarization of the analysis results. Experiments on an Amazon review dataset demonstrate its efficiency, scalability and accuracy. This system could help e-commerce and consumers identify fake reviews, refine product rankings, and constrain vendors and spammers from engaging in dishonest practices.

Learned ontology guided opinions analysis of extracted aspects from online product reviews

Learned ontology guided opinions analysis of extracted aspects from online product reviews

Factors affecting consumers’ online product review use

PurposeThe purpose of this study is to examine factors affecting the extent of consumers’ use of electronic word-of-mouth (eWOM), specifically online product reviews (OPRs), during their decision-making process. It also examines their motives for using OPRs.Design/methodology/approachThe study uses an exploratory qualitative research methodology involving observation and free-flowing face-to-face interviews with consumers who have previously made a purchase online and who read OPRs during the decision-making process. An adaptation of the grounded theory method is used for collection, coding and data analysis.FindingsFindings confirm previously uncovered motives for consumers’ use of OPRs. In addition, the findings suggest that two previously unidentified factors influence the extent of consumers’ use of OPRs: “decision-making drive” and “decision-making drag”. Decision-making drive is a mental momentum created when one or more factors that enhance decision-making readiness are present. This momentum tends to accelerate the decision-making process and shorten the information search process, leading to a reduction in the extent of OPR use. In contrast, decision-making drag is a mental resistance created when one or more factors that impede decision-making readiness are present. This resistance tends to decelerate the decision-making process and lengthen the information search process, leading to an increase in the extent of OPR use.Originality/valueFocused on the pre-consumption phase of eWOM, between the stages of product need recognition and information search, this study is the first to identify decision-making drive and decision-making drag as additional psychological mechanisms affecting the extent of OPR use by consumers. For marketers, understanding these mechanisms has strategic marketing implications that can provide guidance to brands, websites and online review systems.

Linguistic markers of moderate and absolute natural language

In social, personality and mental health research, the tendency to select absolute end-points on Likert scales has been linked to certain cultures, lower intelligence, lower income and personality/mental health disorders. It is unclear whether this response style reflects an absolutist cognitive style or is merely an experimental artefact. In this study, we introduce an alternative, more informative, flexible and ecologically valid approach for estimating absolute responding, that uses natural language markers. We focussed on ‘function words’ (e.g. particles, conjunctions, prepositions) as they are more generalizable because they do not depend on any specific context.To identify such linguistic markers and test their generalizability, we conducted a text analysis of online reviews for films, tourist attractions and consumer products. All written reviews were accompanied by a rating scale (akin to Likert scale), which allowed us to label text samples as absolute/moderate. The data was split into independent ‘training’ and ‘test’ sets. Using the training set we identified a rank order of linguistic markers for absolute and moderate text, which were evaluated in a classifier on the test set. The top three markers alone (“but”, “!” and “seem”) produced 88% classification accuracy, which increased to 91% using 31 linguistic markers.