Online Product Reviews Research Articles

What Makes an Online Review More Helpful: An Interpretation Framework Using XGBoost and SHAP Values

Online product reviews play important roles in the word-of-mouth marketing of e-commerce enterprises, but only helpful reviews actually influence customers’ purchase decisions. Current research focuses on how to predict the helpfulness of a review but lacks a thorough analysis of why it is helpful. In this paper, feature sets covering review text and context cues are firstly proposed to represent review helpfulness. Then, a set of gradient boosted trees (GBT) models is introduced, and the optimal one, which as implemented in eXtreme Gradient Boosting (XGBoost), is chosen to predict and explain review helpfulness. Specially, by including the SHAP (Shapley) values method to quantify feature contribution, this paper presents an integrated framework to better interpret why a review is helpful at both the macro and micro levels. Based on real data from Amazon.cn, this paper reveals that the number of words contributes the most to the helpfulness of reviews on headsets and is interactively influenced by features like the number of sentences or feature frequency, while feature frequency contributes the most to the helpfulness of facial cleanser reviews and is interactively influenced by the number of adjectives used in the review or the review’s entropy. Both datasets show that individual feature contributions vary from review to review, and individual joint contributions gradually decrease with the increase of feature values.

An Examination of the Data Quality of Online Reviews

This research synthesizes the information systems and marketing research by considering the usefulness of online product reviews in the context of Wang and Strong's Data Quality Framework. It examines the extent to which a review's intrinsic (review anonymity and use of personal pronouns), contextual (review length, verified purchase, rating, and rating extremity), and representational quality (spelling errors, grammar errors, readability) impact the perceived usefulness of a product review. The examination of Amazon reviews for an inexpensive experience product revealed number of words, verified purchase, and grammar errors have a significant positive impact on review usefulness. Rating and number of spelling errors have a negative effect, suggesting consumers use some discernment in assessing the believably of a review. Surprisingly, the opposite effect was found for grammar errors, with more grammar errors being associated with a more useful review.

Influencing Knowledge Sharing on Social Media: A Gender Perspective

Online Word-of-Mouth communication, or eWOM, has dramatically changed the way people network, interact, and share knowledge. Studies have examined why consumers choose to share knowledge online, especially online product reviews, as well as the motivations of individuals to share product ideas online. However, the role of gender in shaping the motivation and types of knowledge shared online has been given little consideration. Using concepts from Social Exchange Theory and the Theory of Reasoned Action, we address this research gap by developing and testing a model of gender’s influence on knowledge sharing in a social media context. A PLS analysis of survey data from 257 students indicates that reputation, altruism, and subjective norms are key motivators for knowledge sharing intention in social media. More importantly, that gender plays a moderating role within the motivation-knowledge sharing relationship. We also find that subjective norms have a greater impact on knowledge sharing with women than with men. Collectively, our research results highlight individualized factors for improving customer participation in external facing social media for marketing and product innovation.

Leveraging online customer reviews in new product development: a differential game approach

Large volumes of online product reviews generated by customers have important strategic values for new product development. We consider a duopoly setting where two manufacturers aim to develop their own new products and services. Applying a differential game framework, we examine how online customer reviews can be leveraged as external knowledge for manufacturers to develop new products. In our base models, we assume that the products supplied by the manufacturers are homogenous. First, we consider a closed innovation setting as a benchmark case in which both manufacturers develop new products by their internal R&D without leveraging online customer reviews. Second, we propose a model in which one manufacturer leverages online customer reviews as external knowledge, while the other manufacturer only relies on internal R&D effort. We derive analytical equilibrium solutions to both models. We find that when one manufacturer uses online customer reviews, if the manufacturer’s R&D process becomes more effective in improving its new product performance or reducing its cost, it certainly hurts the other manufacturer, but it may sometimes hurt this particular manufacturer as well. Furthermore, we demonstrate that when the manufacturer utilizes online customer reviews more in R&D, both manufacturers’ profits can either increase or decrease. In an extended model, we relax the product homogeneity assumption and obtain the equilibrium solution analytically. We show that main managerial insights still hold in the extend model.

What Makes Online Review Videos Helpful? Evidence from Product Review Videos on Youtube

With the rapid growth and popularity of YouTube, an increasing number of consumers rely on online product review videos to obtain product-related information. Review videos, with visual and sound cues, can convey product experiences in rich and immersive ways and have a powerful impact on consumer’s perceptions and intentions to purchase the product. As the provision of online review videos grows and consumers increasingly rely on them for their purchase decisions, understanding factors that contribute to the perceived helpfulness of video reviews becomes critical for video review management. This paper examines how various video content characteristics—information accessibility, positivity, and subjectivity—and voice characteristics of reviewers—speech rate, pitch, and speech dynamics—are associated with the perceived helpfulness. We collect detailed data on 14,486 electronic product review videos posted on YouTube and employ speech recognition and natural language processing techniques to extract sentimental and speech characteristics. We find that video viewers perceive online product review videos that are more information-accessible, more positive, and less subjective as more helpful. In addition, review videos created by reviewers with faster speech rates, lower voice pitch, and more vocal dynamicity are perceived as more helpful. We additionally find that reviewers’ popularity can moderate the effect of information accessibility, positivity, and reviewers’ voice characteristics on perceived review helpfulness.

The Adoption of Online Product Information: Cognitive and Affective Evaluations

Online product information (OPI), which is a combination of vendor-supplied product information (VSPI) and online reviews, has become of intense interest to business organizations in their attempt to understand the various ways in which OPI influences consumers. Based on the stimulus-organism-response (SOR) model, this study examined the relationship between mental evaluations of OPI (cognitive and affective evaluations) and the adoption of OPI for both search and experience products. This study used an experimental, custom-designed Web forum built specifically to collect data on how participants evaluated and adopted OPI relating to the purchase of cameras and books. Hypothesis testing was performed using PLS on data collected from 255 participants. Results showed that OPI adoption of information on search products was different from OPI adoption of information on experience products. Both cognitive and affective evaluations affected VSPI adoption, but only cognitive evaluations affected online review adoption. Additionally, VSPI adoption affected online review adoption. Theoretical and practical implications are discussed in the final section.

Research on Sentiment Classification Algorithms on Online Review

The product online review text contains a large number of opinions and emotions. In order to identify the public’s emotional and tendentious information, we present reinforcement learning models in which sentiment classification algorithms of product online review corpus are discussed in this paper. In order to explore the classification effect of different sentiment classification algorithms, we conducted a research on Naive Bayesian algorithm, support vector machine algorithm, and neural network algorithm and carried out some comparison using a concrete example. The evaluation indexes and the three algorithms are compared in different lengths of sentence and word vector dimensions. The results present that neural network algorithm is effective in the sentiment classification of product online review corpus.

IMPACT ANALYSIS OF DIGITAL MARKETING: AN INDIAN PERSPECTIVE

The increasing use of digital media by consumers, companies utilizes digital marketing to outreach their market segments. The purpose of this study is to determine marketing strategies commonly utilized in digital communication and identify the preferred by consumers which influences decision making. Consumers have been identified as a driving force for online shopping. While there have been numerous studies about digital advertising, there has been little academic research focused on type of digital marketing strategies are preferred and influences their consumer’s behavior. A survey of 225 consumes indicated a preference for side panel ads and email ads; they do not like pop – up advertising. If provided a personal benefit like discount or reward they will write an online product review.

Determining Customer Relationship Management Strategy With Customer Personality Analysis Using Ontology Model Approach

Indonesia is a market with attractive e-commerce growth in the past four years. The tight competition made the company try to find ways to maintain customer loyalty, including making improvements to the Customer Relationship Management (CRM) strategy. The way to establish a good CRM strategy is driven by a good approach from the company to customers. Through the process of understanding customer personality, major companies able to understand their customer behaviour, therefore, companies driven by their marketers can perform product marketing activities that are tailored to the tendency of the customer's personality. This research was conducted to determine the personality of the customer by utilizing data obtained from online reviews of several products using the ontology model approach. Personality is measured based on words and phrases given by customers through their online reviews with the help of the Big Five Personality theory in the classification process. The results of this study indicate that the measurement of personality using an ontology model reconstructed with the n-gram algorithm shows that customers on several products have different personalities. These personalities can be used as a foundation in determining and establishing CRM strategies in order to gain higher customer engagement.
 Keywords—Customer Relationship Management; Online Review; Ontology Model; Personality Measurement

SENTIMENT ANALYSIS OF PEOPLE’S ACCEPTANCE TOWARDS THE NEW MALAYSIAN GOVERNMENT USING NAÏVE BAYES METHOD

Sentiment analysis is a field of research that has a significant impact on today’s nations, politics and businesses. It is an algorithmic process to comprehend the opinions of a given subject based on the Natural Language Processing (NLP) methodologies. It has received much attention in recent years and is proven vital in various fields, e.g., online product reviews and social media analysis (Twitter, Facebook, etc.). This paper reports the outcome of sentiment analysis to investigate people’s acceptance of Pakatan Harapan, as the new Malaysian government, spearheaded by Tun Dr. Mahathir Mohamad and Dr. Wan Azizah, with an influence of Dato Seri Anwar Ibrahim. The objective is to classify tweets into three types of sentiments; positive, neutral and negative using Naïve Bayes method which is readily available in Python. The first step is tweets extraction for a month (March to April 2019) using search queries: {Pakatan Harapan, Mahathir, Anwar Ibrahim, Wan Azizah}. It is followed by tweets wrangling using NLP library and lastly output visualization in the form of a word cloud. A word cloud is a visual representation of text data with various font sizes depending on its probabilities. Final results showed that the tweets related to new government consist of neutral sentiment (41%) followed by positive sentiment (30%) and negative sentiment (29%). Malaysians do prefer the new government. However careful mitigation steps must be crafted to overcome controversial issues such as the ‘Rome Statute’ to avoid negative digital footprint, hence winning the Malaysians’ heart.

Dynamic knowledge graph based fake-review detection

Online product reviews are an important driver of customers’ purchasing behavior. Fake reviews seriously mislead consumers, challenging the fairness of the online shopping environment. Although the detection of fake reviews has progressed, several problems remain. First, fake comment recognition ignores the correlation between time and the semantics of the comment texts, which is always hidden in the context of the reviews. Second, the impact of multi-source information on fake comment recognition is not considered, as it constitutes a complex, high-dimensional, heterogeneous relationship between reviewers, reviews, stores and commodities. To overcome these problems, the present paper proposes a dynamic knowledge graph-based method for fake-review detection. Based on the characteristics of online product reviews, it first extracts four types of entities using a developed neural network model called sentence vector/twin-word embedding conditioned bidirectional long short-term memory. Time series related features are then added to the knowledge graph construction process, forming dynamic graph networks. To enhance the fake-review detection, four indicators are newly defined for determining the relationships among the four types of nodes. In experimental evaluations, our method surpassed the state-of-the-art results.

Calibration of Voting-Based Helpfulness Measurement for Online Reviews: An Iterative Bayesian Probability Approach

Voting mechanisms are widely adopted for evaluating the quality and credibility of user-generated content, such as online product reviews. For the reviews that do not receive sufficient votes, techniques and models are developed to automatically assess their helpfulness levels. Existing methods serving this purpose are mostly centered on feature analysis, ignoring the information conveyed in the frequencies and patterns of user votes. Consequently, the accuracy of helpfulness measurement is limited. Inspired by related findings from prediction theories and consumer behavior research, we propose a novel approach characterized by the technique of iterative Bayesian distribution estimation, aiming to more accurately measure the helpfulness levels of reviews used for training prediction models. Using synthetic data and a real-world data set involving 1.67 million reviews and 5.18 million votes from Amazon, a simulation experiment and a two-stage data experiment show that the proposed approach outperforms existing methods on accuracy measures. Moreover, an out-of-sample user study is conducted on Amazon Mechanical Turk. The results further illustrate the predictive power of the new approach. Practically, the research contributes to e-commerce by providing an enhanced method for exploiting the value of user-generated content. Academically, we contribute to the design science literature with a novel approach that may be adapted to a wide range of research topics, such as recommender systems and social media analytics.

Online Reviews: What Drives Consumers to Use Them

ABSTRACT With the rapid E-commerce growth and changes in consumers’ behaviors, many businesses are forced to adapt their business model to match their target customers’ needs. To provide consumers with more product details and increase their confidence in making online purchases, online businesses offer online reviews as an alternative to customers physically interacting with a product. Although consumers have become familiar with the use of online product reviews, many aspects of users’ perceptions of online reviews are still not well understood. This study explores the factors underlying the intention of Thai consumers to use online reviews when considering purchasing an item. The study results provide insight into the factors that affect consumers’ use of online reviews prior to a purchase. This study furthers the body of knowledge that deals with online reviews and system use, providing results that allow E-businesses to adapt their business model to better fit consumers’ expectations.

Discussion of \u201cThe Market for Reviews: Strategic Behavior of Online Product Reviewers with Monetary Incentives\u201d

In this note, I discuss the article of Dorner et al. who experimentally study the issue of generating high-quality online product reviews under two different incentive schemes. I first classify their work in the existing literature on marketing and information systems and highlight their contribution. I then argue that the existence of cognitive dissonance costs serve as a reasonable explanatory factor for their main results. Two further critical issues warn against the limited generalizability of the present study to the real review market and ability to provide practical implications.

Brunt of Online Product Reviews over Customers Assessment on Online Platform Instagram

The purpose of the study is to understand the attitude of consumers towards user-generated content (UGC) in relation to brand or expert feedback when it comes to online product reviews given by other users. This research explored the role of various contexts, perceived usefulness, perceived risk, perceived credibility, the intention of review valance, review source, and purchase. This study has also attempted to comprehend influence over customer’s attitudes towards UGC and explored its contributions to the perceived intention to buy. Every antecedent has a distinct impact on the buying mindset and intention. The goal of this analysis is to investigate how these contexts impact the attitude of customers towards UGC individually.

Impact of Brand Strength and Customer Reviews: The Case of Rural Tourism Inns in China

As e-commerce continues to become an integral part of our lives, more and more purchase decisions are being made online. A significant contribution leading to such purchases stem from a few key factors, one of which, is customer reviews. Reviews are based on consumer experience and are increasingly necessary on e-commerce sites and platforms. Another key factor is the role brands play in influencing purchase decisions. A brand is an intangible asset of a company where brand value reflects the degree of differentiation a brand has over competitors. Most consumers judge the quality of an online product based on reviews and brands. This paper explores the question of how online product reviews and brands affect product sales on travel websites, using Ctrip.com as a case study. The study uses the user recommendation rate, the total score, the total number of reviews and brand strength to draw a relationship that suggests online reviews and brand strength impact product sales. The results demonstrate that there is a positive impact on product sales for high review scores on weak-branded inns; and the sales volume of strongbranded inns are more prominently affected by the number of comments and user recommendation rate.

Excellent Product … But Too Early to Say: Consumer Reactions to Tentative Product Reviews

This research explores the effects of tentativeness in online product reviews on consumers' product attitude certainty and behavioral intentions. Drawing on salience theory, attribution theory, and work in attitude certainty, I predict that, when consumers who have seen positive reviews of a product are exposed to a tentative review, their attitude certainty and willingness to purchase is reduced. I also predict that consumer reactions differ depending on the expertise of the review source as well as the product experience of the consumer.I also address confidence in information completeness as the metacognitive mechanism that explains the tentative review effect. Specifically, I argue that consumers who see a tentative review are sensitized to potentially missing information, which reduces their attitude certainty and willingness to purchase.Our hypotheses are tested in a series of experiments which demonstrate that tentativeness reduces attitude certainty and willingness to purchase but that the effect is attenuated when the reviewer is a novice and when the consumer has a high level of product experience. Based on the findings, I discuss our contributions to theory and suggest practical steps that firms can take to mitigate the effects of tentative reviews.

Big Data Management and Analytics in Scientific Programming: A Deep Learning-Based Method for Aspect Category Classification of Question-Answering-Style Reviews

Online product reviews are exploring on e-commerce platforms, and mining aspect-level product information contained in those reviews has great economic benefit. The aspect category classification task is a basic task for aspect-level sentiment analysis which has become a hot research topic in the natural language processing (NLP) field during the last decades. In various e-commerce platforms, there emerge various user-generated question-answering (QA) reviews which generally contain much aspect-related information of products. Although some researchers have devoted their efforts on the aspect category classification for traditional product reviews, the existing deep learning-based approaches cannot be well applied to represent the QA-style reviews. Thus, we propose a 4-dimension (4D) textual representation model based on QA interaction-level and hyperinteraction-level by modeling with different levels of the text representation, i.e., word-level, sentence-level, QA interaction-level, and hyperinteraction-level. In our experiments, the empirical studies on datasets from three domains demonstrate that our proposals perform better than traditional sentence-level representation approaches, especially in the Digit domain.

May we buy your love? psychological effects of incentives on writing likelihood and valence of online product reviews

Acknowledging the impact on their sales, companies strive to increase the number of positive online reviews of their products. A recently popular practice for stimulating online reviews is offering monetary rewards to customers in return for writing an online review. However, it is unclear whether such practices succeed in fulfilling two main objectives, namely, increasing the number and the valence of online reviews. With one pilot and two experimental studies, this research shows that offering incentives indeed increases the likelihood of review writing. However, the effect on review valence is mixed, due to contradictory psychological effects: Incentive recipients intend to reciprocate by writing favorable reviews but also perceive a need to resist marketers’ influence, which negatively affects their review valence. Finally, recipients who are less satisfied with the product are particularly prone to psychological costs and decrease the positivity of their online reviews. Consequently, incentives should be applied carefully.

Design of a Category Independent, Aspect Based Automated Opinion Analysis Technique for Online Product Reviews

ABSTRACT Customer feedback in the form of online reviews is an important source of information to manufacturers or service providers for evaluation of their products or services. Online reviews also help potential buyers in making their decisions. Manual checking of these huge amount of unstructured texts is time consuming. Several attempts have been made for opinion aggregation of online reviews but a generalized automated technique has yet to be developed. In this work, an efficient rule based technique for aspect wise summarization of online product reviews irrespective of their categories has been designed. The proposed technique develops the rules for extracting aspects and associating the opinion words to the respective aspects followed by effective grouping and summarization of aspect-opinion pairs into human interpretable form. The algorithm has been implemented on Amazon Product Reviews and evaluated against manually annotated ground truth. The result shows promising similarity with human judgement.