Mining the text of online consumer reviews to analyze brand image and brand positioning

The growth of the Internet has led to massive availability of online consumer reviews. So far, papers studying online reviews have mainly analysed how non-textual features, such as ratings and volume, influence different types of consumer behavior, such as information adoption decisions or product choices. However, little attention has been paid to examining the textual aspects of online reviews in order to study brand image and brand positioning. The text analysis of online reviews inevitably raises the concept of “text mining”; that is, the process of extracting useful and meaningful information from unstructured text. This research proposes an unified, structured and easy-to-implement procedure for the text analysis of online reviews with the ultimate goal of studying brand image and brand positioning. The text mining analysis is based on a lexicon-based approach, the Linguistic Inquiry and Word Count (Pennebaker et al., 2007), which provides the researcher with insights into emotional and psychological brand associations.     

消费者后悔理论研究综述

感觉是为了行为(feeling is for doing),大量的实证研究证实了后悔这一情绪对消费者的众多决策行为有重要的影响作用。本文通过文献回顾总结后悔的内涵、实验与测量方式、影响因素和在消费者决策领域中的应用等内容,最后指出后悔这一情绪在消费者决策研究领域中的重要意义。     

Aesthetics and the online shopping environment: Understanding consumer responses

As the e-tail industry continues to grow with increasing competition witnessed, the study of how to entice and retain online customers has never been as important as at present. Our hierarchical model examines how the two dimensions of web aesthetics, aesthetic formality and aesthetic appeal, influence online consumers’ psychological reactions, including perceived service quality, satisfaction, and arousal, and how these psychological changes, in turn, influence online consumers’ conative tendencies. The results indicate: (1) consumers’ cognitive, affective, and conative outcomes can be significantly evoked by aesthetic stimuli; (2) the two dimensions of web aesthetics exhibit dissimilar patterns of influences; and (3) purchase task significantly moderates consumers’ responses in terms of magnitude and direction. The study provides practical guidelines for properly manipulating the two dimensions of web aesthetics based on consumers’ motivational orientations.     

Status reinforcing: Unintended rating bias on online shopping platforms

Online shopping platforms have gradually begun to use hierarchical loyalty programs to distinguish customers. Previous studies have focused mainly on the effect of such programs on loyalty and repurchase behavior, and little is known about how customer statuses in hierarchical loyalty programs affect their online product evaluations. Drawing on social status and social conformity theory, this study investigates the impact of customer status on the valence of online reviews. An instrumental variable is proposed to address the endogeneity issue. The results show that a customer's need for status leads to a negative rating bias when leaving online reviews. At the same time, people encounter social pressure from crowds. The need for social conformity can alleviate such rating bias. This study contributes to the understanding of the effect of social status on post-purchase behavior and provides practical implications for both managers and platforms.     

Consequences of personalized product recommendations and price promotions in online grocery shopping

Shopping convenience can be turned into a competitive advantage for online grocery retailers. Consequently, we study how personalized product recommendations (recommendation agents) and price promotions (algorithmic pricing) compensate for the negative impact that consumer's perceived cognitive effort causes on loyalty. By default, the relationship from perceived cognitive efforts to attitudinal and behavioral loyalty is negative, yet these results demonstrate that personalized price promotions lessen the negative impact, while personalized product recommendations do not have such an influence. The findings contribute to a better understanding of personalized marketing activities in today's data-driven online grocery retailing.     

Creating and detecting fake reviews of online products

Customers increasingly rely on reviews for product information. However, the usefulness of online reviews is impeded by fake reviews that give an untruthful picture of product quality. Therefore, detection of fake reviews is needed. Unfortunately, so far, automatic detection has only had partial success in this challenging task. In this research, we address the creation and detection of fake reviews. First, we experiment with two language models, ULMFiT and GPT-2, to generate fake product reviews based on an Amazon e-commerce dataset. Using the better model, GPT-2, we create a dataset for a classification task of fake review detection. We show that a machine classifier can accomplish this goal near-perfectly, whereas human raters exhibit significantly lower accuracy and agreement than the tested algorithms. The model was also effective on detected human generated fake reviews. The results imply that, while fake review detection is challenging for humans, “machines can fight machines” in the task of detecting fake reviews. Our findings have implications for consumer protection, defense of firms from unfair competition, and responsibility of review platforms.     

Beyond adoption: sustaining online shopping

Online retailing has the potential to offer remote areas a wider marketplace for their retail products and also a concomitant increase in income. Drawing on secondary Internet-based research, this paper considers the fortunes and future of online retailing in a number of the remote British Overseas Territories. It will become apparent that Internet retailing is an important strategic option for retailers in such isolated locations, but greater attention needs to be paid to issues surrounding operations and logistics, payment systems and merchandising. It is also seen how, despite its apparent ‘placelessness’, the Internet and associated online selling cannot escape the realities of space and distance.     

Does culture affect sentiments expressed in cruise tours’ eWOM?

The study aims to examine the sentiment differences in the content of cruise tour online reviews across North Americans and Europeans, as representing the two largest cruise markets. Dictionary-based sentiment analysis has been carried out on 1127 reviews on guided tours retrieved from TripAdvisor. The results indicate significant differences in the sentiment score of the reviews, with North Americans’ texts being more emotionally charged than the European ones. In addition, North Americans’ reviews conveyed a more positive affect and had a more subjective and intimate tone, while those written by Europeans contained a smaller amount of sentiment-bearing words and their tone was more objective. The study’s contribution lies in (i) providing evidence for the influence of culture on electronic word-of-mouth communication in terms of varying sentiment expression, (ii) demonstrating the effectiveness of sentiment analysis for recognizing cultural differences and (iii) enhancing the current understanding of cruisers’ tour experience.     

A comparison of online and offline consumer behaviour: An empirical study on a cinema shopping context

The main objective of this study is to analyse online vs. offline differences in consumer behaviour. To this end, through a proposal applied to cinemas in shopping centres, this study considers values and lifestyles as major factors that influence behaviours and intentions. The partial least squares (PLS) approach is used to evaluate the model. A multi-group analysis is conducted to compare consumers who buy tickets online with those who do so at a box office. We consider 391 valid cases. The results obtained show a link between the use of technology and its effects on behaviour. The relationships between values and behaviour as well as between behaviour and future intent are stronger among online consumers than the effects of lifestyles on behaviour. We consider relevant theoretical and empirical perspectives and offer critical recommendations of use to shopping centre managers, movie theatres, and intermediaries of this sector.     

Hedonic and utilitarian shopping goals: The online experience

Marketers offering Web-based shopping typically try to provide a convenient, safe, and pleasant online environment, appropriate to addressing shoppers' functional goals. They might also try to create an experience that encourages more escapist elements of “flow”, a sense of deep involvement that is intrinsically enjoyable, because they assume that this enhanced experience leads to more online buying. The present research suggests that utilitarian flow elements that facilitate shopping may indeed increase purchasing. However, hedonic elements of flow are found to be unrelated to online buying, although they are positively related to outcomes associated with pathological Internet use.     

Untangling the relationships between consumer characteristics,shopping values,and behavioral intention in online group buying

This study examines the link among consumer characteristics (price-sensitive behavior, variety-seeking behavior, and compulsive buying behavior), shopping values (utilitarian and hedonic shopping values), and behavioral intention in online group buying (OGB). This study tests usable responses collected by means of mall-intercept systematic sampling from consumers who previously participated in OGB. Structural equation modeling was used to analyze data and test the hypothesized relationships. Findings suggest that price-sensitive and variety-seeking behaviors are significantly related to utilitarian shopping value, whereas price-sensitive, variety-seeking, and compulsive buying behaviors are significantly related to hedonic shopping value. Both utilitarian and hedonic shopping values significantly influence consumers’ OGB intentions. For a successful OGB strategy, Internet marketers and site operators should emphasize the utilitarian shopping value of price saving and selection and introduce the hedonic shopping values of promotions and sensory experiences. This study provides a link between two streams of prior research – that is, consumer characteristics and shopping values. Furthermore, it validates an empirical model whose results can help business practitioners make better-informed marketing management decisions for OGB and help academics and consumers better understand OGB behavior.     

The fluent online shopping experience

Consumers increasingly use various Internet-enabled devices for online shopping; thus, a critical topic for both research and practice is the visual characteristics of the information presented in this medium. This study builds on fluency theory within an environmental psychology framework. Specifically, this research examines how consumers' perceived fluency of the verbal online information affects their perceived cognitive effort and positive affect within a choice context. The experimental results show that (1) perceptual fluency affects both cognitive effort and positive affect experienced during online shopping and (2) cognitive effort and positive affect influence judgments about the perceived decision quality of the choice made. This research is notable in its simultaneous (as opposed to consecutive) examination of the relationship among the three dimensions of processing fluency (perceptual fluency, positive affect, and cognitive effort) and their impact on consumers' choice satisfaction with an online shopping task.     

The effects of eWOM characteristics on consumer ratings: evidence from TripAdvisor.com

Abstract

Given the rise of online review communities, the management of consumer ratings has gained much attention in the recent years. In this study, we use data from Tripadvisor.com and examine the number of stars that a review receives. Specifically, we address how a star rating is determined by the components in the focal review as well as the preceding reviews of other consumers. Our qualitative and quantitative analyses provide interesting findings as follows. A star rating has a positive relationship with the focal review’s valence. That is, the more positive a review is, the greater number of stars a review receives. The reviews of other consumers also play a role in determining a star rating of the focal review suggesting social influence among consumers. Interestingly, a review with lengthy content leads to a lower star rating only when using smartphones. We conclude with theoretical and managerial implications.     

Toward a conceptualization of the online shopping experience

This research article explores the content of consumers′ experience when they shop online and proposes a first step in conceptualizing the ‘online shopping experience′ (OSE). First, we carried out an extended literature review and proposed an integrative conceptual framework. Then, we relied on a consumers discourse analysis with four focus groups with consumers who differ in terms of age, gender and online shopping experience.We define the OSE and propose a conceptualization through four core dimensions: the physical, ideological, pragmatic and social dimensions. Connections are established between the flow concept and the ‘traditional’ dimensions of experience, and specific shopping values are identified. Moreover, an appropriation process of commercial websites is revealed; beyond purchase intentions and rituals, the OSE is embodied by the use of online tools and patronage routines. Finally, social interactions with Facebook friends are one of the new practices considered.     

A model of adolescents' online consumer self-efficacy (OCSE)

This paper investigates adolescent online shopping and self-efficacy development in the virtual setting. The authors present and test a model of antecedents and mediators to two dimensions of online consumer self-efficacy. Additionally, a discriminant analysis finds that more involved adolescent online shoppers can be differentiated from less involved online shoppers on key variables of interest-shopping motivations, self-efficacies, shopping behaviors, and relative influence in household decision-making.     

A comparison of online and offline gender and goal directed shopping online

The aim of this paper is to model the effect of the consumers’ perceptions of their offline and online gendered behaviour on online utilitarian shopping motivation and purchase intentions. We hypothesise that when consumers shop online, their behaviour is mediated by two gendered behaviours, namely offline and online. To test this hypothesis, 515 usable responses were collected in face-to-face interviews. The conceptual model was tested with confirmatory factors analysis (CFA) and structural equation modelling (SEM) across five product categories. Our findings show that the effect of a consumer's perception of their gendered behaviour offline vs. online on online utilitarian shopping motivation and purchase intentions is significantly different. In particular we found that utilitarian shopping motivation online has a significant effect on purchase intentions online mediated by gender (online) overall: strongly for females but not for males. Conversely, utilitarian shopping motivation online has a significant effect on purchase intentions online mediated by gender (offline) for males but not overall and for females.     

An empirical comparison of machine learning methods for text-based sentiment analysis of online consumer reviews

The amount of digital text-based consumer review data has increased dramatically and there exist many machine learning approaches for automated text-based sentiment analysis. Marketing researchers have employed various methods for analyzing text reviews but lack a comprehensive comparison of their performance to guide method selection in future applications. We focus on the fundamental relationship between a consumer’s overall empirical evaluation, and the text-based explanation of their evaluation. We study the empirical tradeoff between predictive and diagnostic abilities, in applying various methods to estimate this fundamental relationship. We incorporate methods previously employed in the marketing literature, and methods that are so far less common in the marketing literature. For generalizability, we analyze 25,241 products in nine product categories, and 260,489 reviews across five review platforms. We find that neural network-based machine learning methods, in particular pre-trained versions, offer the most accurate predictions, while topic models such as Latent Dirichlet Allocation offer deeper diagnostics. However, neural network models are not suited for diagnostic purposes and topic models are ill equipped for making predictions. Consequently, future selection of methods to process text reviews is likely to be based on analysts’ goals of prediction versus diagnostics.     

Increasing online sales by facilitating spillover shopping

The Internet can serve dual roles as a source of information and a shopping channel for consumers. As a source of information, it competes with traditional sources such as print and direct mail. As a shopping channel, it competes with traditional shopping formats such as brick-and-mortar retailing and catalogs. There is little research as yet, however, regarding how the use of the online channel for information can affect its use for purchasing products. Our research is aimed at filling this gap in the literature, i.e., of examining if and how the use of the Internet as a source of information can affect consumers’ willingness to shop online. We use an integrated modeling framework that simultaneously models consumers’ choice of a shopping channel from three options – brick and mortar, catalog and online – and a source of information from three options as well: newspapers and magazines, direct mail, and online.     

Intra-household task allocation in online grocery shopping: Together alone

This paper explores how households organize the process of e-grocery buying in a click-and-collect context, down to the level of the two main subtasks: the online ordering and the picking-up. Self-collected survey data on 112 users of Belgian click-and-collect services first provide a quantitative perspective. But we primarily exploit in-depth interviews with 15 households. Both our quantitative and qualitative findings indicate that women today are still the main responsible for grocery shopping, even in an online context. Especially the ordering is a woman's task; the collecting is more equally divided across genders. But the key result is that couples exploit the opportunities for further task division provided by e-grocery shopping. In our survey we find that in 72.5% of the couples both partners are involved in the process, but that in roughly three quarters of these cases at least one of the tasks is performed independently. In other words, many couples do it ‘together alone’. Our qualitative analysis further shows that the roles of the partners have become more fixed, in that subtasks are assigned exclusively to one partner. As for the reasons behind the task allocation, we find indications of the relevance of time availability, relative resource, and gender arguments (respectively, the presence of young children, imbalances in educational status and income, and traditional roles), but also of purely pragmatic reasons.