Search results

The purpose of this paper is to suggest important determinants for helpfulness from the reviews’ product data, review characteristics, and textual characteristics, and identify the more crucial factors among these determinants by using statistical methods. Furthermore, this study intends to propose a classification-based review recommender using a decision tree (CRDT) that uses a decision tree to identify and recommend reviews that have a high level of helpfulness.

This study used publicly available data from Amazon.com to construct measures of determinants and helpfulness. To examine this, the authors collected data about economic transactions on Amazon.com and analyzed the associated review system. The final sample included 10,000 reviews composed of 4,799 helpful and 5,201 not helpful reviews.

The study selected more crucial determinants from a comprehensive group of product, reviewer, and textual characteristics through using a t-test and logistics regression. The five important variables found to be significant in both t-test and logistic regression analysis were the total number of reviews for the product, the reviewer’s history macro, the reviewer’s rank, the disclosure of the reviewer’s name, and the length of the review in words. The decision tree method produced decision rules for determining helpfulness from the value of the product data, review characteristics, and textual characteristics. The prediction accuracy of CRDT was better than that of the k-nearest neighbor (kNN) method and linear multivariate discriminant analysis in terms of prediction error. CRDT can suggest better determinants that have a greater effect on the degree of helpfulness.

The important factors suggested as affecting review helpfulness should be considered in the design of websites, as online retail sites with more helpful reviews can provide a greater potential value to customers. The results of the study suggest managers and marketers better understand customers’ review and increase the value to customers by proving enhanced diagnosticity to consumers.

This study is different from previous studies in that it investigated the holistic aspect of determinants, that is, product, review, and textual characteristics for classifying helpful reviews, and selected more crucial determinants from a comprehensive group of product, reviewer, and textual characteristics by using a t-test and logistics regression. This study utilized a decision tree, which has rarely been used in predicting review helpfulness, to provide rules for identifying helpful online reviews.

This paper aims to find determinants that can predict the helpfulness of online customer reviews (OCRs) with a novel approach.

The approach consists of feature engineering using various text mining techniques including BERT and machine learning models that can classify OCRs according to their potential helpfulness. Moreover, explainable artificial intelligence methodologies are used to identify the determinants for helpfulness.

The important result is that the boosting-based ensemble model showed the highest prediction performance. In addition, it was confirmed that the sentiment features of OCRs and the reputation of reviewers are important determinants that augment the review helpfulness.

Each online community has different purposes, fields and characteristics. Thus, the results of this study cannot be generalized. However, it is expected that this novel approach can be integrated with any platform where online reviews are used.

This paper incorporates feature engineering methodologies for online reviews, including the latest methodology. It also includes novel techniques to contribute to ongoing research on mining the determinants of review helpfulness.

While a number of studies examined the eWOM (online word-of-mouth) factors affecting box office, the studies on the impact of review helpfulness on box office are lacking. The purpose of this paper is to fill the void in previous studies and further extend prior work regarding eWOM and box office. In order to explain the interaction effect of helpfulness with other variables on product sales, this study posits that review characteristics such as number of reviews, review rating, review length interact with review helpfulness to have an influence on box office. Further, as the studies that have examined whether eWOM factors are significant in box office performances for the international markets other than US are lacking, this study is targeting Korean markets to validate the effect of eWOM on box office.

This study used publicly available data from www.naver.com to build a sample of online review data concerning box office. The final sample of the study included 2090 movies.

The results indicated that in cases when the review is helpful, the number of reviews and review length are more greatly influencing box office. Review rating, review extremity, and helpfulness for reviewer are important determinants for review helpfulness.

Managers can concentrate on the review rating and review extremity of online customer reviews in the design of online sites for movies. The design of user review systems can follow the direction that promotes more helpfulness for online user reviews based on an enhanced understanding of what drives helpfulness voting.

Given that previous studies on the effect of review helpfulness on box office are lacking, it contributes to eWOM literature by investigating the impact of review helpfulness on box office revenue.

The prevalence of online review websites and the ever-growing difficulty of judging review quality result in the increasing need for consumers to reduce cognitive costs. Thus, the purpose of this study is to find out the determinants of review helpfulness based on a comprehensive theoretical framework and empirical model.

This study applied a comprehensive framework, including both review content quality and reviewer background, to investigate the determinants of review helpfulness. It also presents empirical models to further control factors around product features.

Consumers are more likely to give helpful votes to those informative and readable reviews accompanied by extreme ratings. Reviewers who disclose information, have a high reputation and report a poor experience are always identified as helpful. Consumers also tend to signal suggestions from users with a local cultural background as subjective and useless.

This study focuses on upscale hotels in China. Information registered on TripAdvisor was used presenting a residential address not nationality. Only few controlling factors available because of the limited information are shown on online review websites.

Managers of both hotels and online review websites need to focus on reviews and/or reviewers as KOLs who attract consumers’ attention and affect their subsequent decisions. A dialogue with those KOLs can be by focusing on responding to reviews with certain characteristics. A reward system for reviews and KOLs may benefit review quality on online review websites and reduce cognition costs.

This positivistic research design, with multilevel approach, presenting a comprehensive conceptual framework and empirical model not only considering review- and reviewer-related factors but also controlled factors in product or service level (hotel-related characteristics).

This study aims to uncover how heuristic information cues (HIC) and systematic information cues (SIC) of online reviews influence review helpfulness and examine a moderating role of social influence in the process of assessing review helpfulness. In particular, this study conceptualizes a theoretical framework based on dual-process and social influence theory (SIT) and empirically tests the proposed hypotheses by analyzing a broad set of actual customer review data.

For 4,177,377 online reviews posted on Yelp.com from 2004 to 2018, this study used data mining and text analysis to extract independent variables. Zero-inflated negative binomial regression analysis was conducted to test the hypothesized model.

The present study demonstrates that both HIC and SIC have a significant relationship with review helpfulness. Normative social influence cue (NSIC) strengthened the relationship between HIC and review helpfulness. However, the moderating effect of NSIC was not valid in the relationship between SIC and review helpfulness.

This study contributes to the extant research on review helpfulness by providing a conceptual framework underpinned by dual-process theory and SIT. The study not only identifies determinants of review helpfulness but also reveals how social influences can impact individuals’ judgment on review helpfulness. By offering a state-of-the-art analysis with a vast amount of online reviews, this study contributes to the methodological improvement of further empirical research.

本论文旨在揭示网络评论的启发性信息源和系统性信息源对于评论有用性的影响, 以及检验社会影响在评论有用性的调节作用。其中, 本论文基于双重历程理论和社会影响理论来构建理论模型, 并且利用实际数据来验证假设, 通过分析一系列实际客户评论数据。

本论文样本数据为2004年至2018年Yelp.com上面的4,177,377网络评论。本论文采用数据挖掘和文本分析的方法来提取自变量。本论文采用零膨胀负二项回归模型来验证假设。

研究结果表明, 启发性和系统性信息源都对网络评论有用性有着显著作用。规范性社会影响加强了启发性信息源对评论有用性的作用。然而, 规范性社会影响对系统性信息源与评论有用性的关系并未起到有效的调节作用。

本论文对现有评论有用性的文献有着补充贡献, 其采用双重历程理论和社会影响理论来构建理论模型。本论文不仅指出评论有用性的影响因素, 而且展示了社会影响如何影响个人对评论有用性的判断。本论文的样本数据庞大, 数据分析夯实, 这对于进一步的实际测量研究有着方法改进方面的贡献。

The purpose of this study is to present a methodology for enhancing the quality and usefulness of online reviews for prospective customers to investigate how this contemporary form of instrumental support can be facilitated to strengthen customer-to-customer support.

This study develops an analytics framework with applications of machine learning models using customer review data from Amazon.com. Linear regression is commonly used for review helpfulness and sales prediction. In this study, Random Forest model is applied because of its strong performance and reliability. To advance the methodology, a custom script in Python is created to generate Partial Dependence Plots for intensive exploration of the dependency interpretations of review helpfulness and sales. The authors also apply K-Means to cluster reviewers and use the results to generate reviewer qualification scores and collective reviewer scores, which are incorporated into the review facilitation process.

The authors find the average helpfulness ratio of the reviewer as the most important determinant of reviewer qualification. The collective reviewer qualification for a product created based on reviewers’ characteristics is found important to customers’ purchase intentions and can be used as a metric for product comparison.

The findings of this study suggest that service improvement efforts can be performed by developing software applications to monitor reviewer qualifications dynamically, bestowing a badge to top quality reviewers, redesigning review sorting interfaces and displaying the consumer rating distribution on the product page, resulting in improved information reliability and consumer trust.

This study adds to the research on customer-to-customer support in the service literature. As customer reviews perform as a contemporary form of instrumental support, the authors validate the determinants of review helpfulness and perform an intensive exploration of its dependency interpretation. Reviewer qualification and the collective reviewer qualification scores are generated as new predictors and incorporated into the helpfulness-based review facilitation services.

Big data analytics allows researchers and industry practitioners to extract hidden patterns or discover new information and knowledge from big data. Although artificial intelligence (AI) is one of the emerging big data analytics techniques, hospitality and tourism literature has shown minimal efforts to process and analyze big hospitality data through AI. Thus, this study aims to develop and compare prediction models for review helpfulness using machine learning (ML) algorithms to analyze big restaurant data.

The study analyzed 1,483,858 restaurant reviews collected from Yelp.com. After a thorough literature review, the study identified and added to the prediction model 4 attributes containing 11 key determinants of review helpfulness. Four ML algorithms, namely, multivariate linear regression, random forest, support vector machine regression and extreme gradient boosting (XGBoost), were used to find a better prediction model for customer decision-making.

By comparing the performance metrics, the current study found that XGBoost was the best model to predict review helpfulness among selected popular ML algorithms. Results revealed that attributes regarding a reviewer’s credibility were fundamental factors determining a review’s helpfulness. Review helpfulness even valued credibility over ratings or linguistic contents such as sentiment and subjectivity.

The current study helps restaurant operators to attract customers by predicting review helpfulness through ML-based predictive modeling and presenting potential helpful reviews based on critical attributes including review, reviewer, restaurant and linguistic content. Using AI, online review platforms and restaurant websites can enhance customers’ attitude and purchase decision-making by reducing information overload and search cost and highlighting the most crucial review helpfulness features and user-friendly automated search results.

To the best of the authors’ knowledge, the current study is the first to develop a prediction model of review helpfulness and reveal essential factors for helpful reviews. Furthermore, the study presents a state-of-the-art ML model that surpasses the conventional models’ prediction accuracy. The findings will improve practitioners’ marketing strategies by focusing on factors that influence customers’ decision-making.

We investigate the joint impacts of three trust cues – content, sentiment and helpfulness votes – of online product reviews on the trust of reviews and attitude toward the product/service reviewed.

We performed three studies to test our research model, presenting participants with scenarios involving product reviews and prior users' helpful and unhelpful votes across experimental settings.

A high helpfulness ratio boosts users’ trust and influences behaviors in both positive and negative reviews. This effect is more pronounced in attribute-based reviews than emotion-based ones. Unlike the ratio effect, helpfulness magnitude significantly impacts only negative attribute-based reviews.

Future research should investigate voting systems in various online contexts, such as Facebook post likes, Twitter microblog thumb-ups and up-votes for article comments on platforms like The New York Times.

Our findings have significant implications for voting system-providers implementing information techniques on third-party review platforms, participatory sites emphasizing user-generated content and online retailers prioritizing product awareness and reputation.

This study addresses an identified need; that is, the helpfulness votes as an additional trust cue and the joint effects of three trust cues – content, sentiment and helpfulness votes – of online product reviews on the trust of customers in reviews and their consequential attitude toward the product/service reviewed.

In the field of hospitality, most studies use English reviews and neglect non-English sources. The purpose of this paper is to exploit a predictive framework for review helpfulness that can process both Chinese and English textual comments.

This study develops some methods for feature extraction from Chinese online reviews, extracts more comprehensive predictors and proposes a novel prediction framework of classification before regression. Hofstede’s cultural theory is used to explain differences in the determinants of the helpfulness of reviews in Chinese and English.

The findings reveal that travelers from various countries do have discrepant perspectives on reviews helpfulness. Chinese tourists pay more attention to the reviewer profiles, whereas American tourists pay more attention to the review-related features.

This research offers hoteliers with actionable implications for meeting the needs of travelers from dissimilar cultural societies. The authors’ prediction framework can be used by website developers to create a review helpfulness rating system that allows visitors to acquire beneficial information.

On the one hand, the methods developed for extracting features of Chinese review, the hybrid set of features with several novel predictors and the prediction framework proposed in this study contribute to the methodology. On the other hand, this study is one of the few articles based on Hofstede’s cultural theory to guide a cross-cultural study on reviews helpfulness in hotel sector, which in turn contributes to the theory.

Consumers’ evaluation of online review helpfulness has been widely examined. The extant literature suggests that the attributes of review content (e.g. review length and extremity) influence review helpfulness. However, review length cannot fully reflect the richness of the review content. Anchoring on information diagnosticity and extremity bias, this study aims to explore the effect of review comprehensiveness on its helpfulness.

Field observations were obtained from 11,812 online restaurant reviews on a popular restaurant review platform. A controlled experiment was conducted to further delineate the effect of review comprehensiveness.

Review comprehensiveness moderates the effects of review length and an extremely negative review on helpfulness. It also confirms that for reviews of the same length, one covering more aspects is perceived by consumers as more helpful.

Different aspects of information in a review can efficiently assist decision-making. The results suggest that review platforms can better design their interface by providing separate areas for different product aspects. The platform can then receive more comprehensive and helpful reviews and increase the diagnosticity of these.

The study enriches the literature by introducing review comprehensiveness and examining the joint effects of review length and comprehensiveness on helpfulness. It also contributes to the literature by indicating how to reduce the effect of review extremity.