Volume Of Online Reviews Research Articles

Tree hierarchical deep convolutional neural network optimized with sheep flock optimization algorithm for sentiment classification of Twitter data

ABSTRACT The increasing volume of online reviews and tweets poses significant challenges for sentiment classification because of the difficulty in obtaining annotated training data. This paper aims to enhance sentiment classification of Twitter data by developing a robust model that improves classification accuracy and computational efficiency. The proposed method named Tree Hierarchical Deep Convolutional Neural Network optimized with Sheep Flock Optimization Algorithm for Sentiment Classification of Twitter Data (SCTD-THDCNN-SFOA) utilizes the Stanford Sentiment Treebank dataset. The process begins with pre-processing steps including Tokenization, Stop words Elimination, Filtering, Hashtag Removal, and Multiword Grouping. The Gray Level Co-occurrence Matrix Window Adaptive Algorithm is employed to extract features, such as emoticon counts, punctuation counts, gazetteer word existence, n-grams, and part of speech tags. These features are selected using Entropy–Kurtosis-based Feature Selection approach. Finally, the Tree Hierarchical Deep Convolutional Neural Network enhanced by the Sheep Flock Optimization Algorithm is used to categorize the Twitter data as positive, negative, and neutral sentiments. The proposed SCTD-THDCNN-SFOA method demonstrates superior performance, achieving higher accuracy and lesser computation time than the existing models, respectively. The SCTD-THDCNN-SFOA framework significantly improves the accuracy and efficiency of sentiment classification for Twitter data.

Optimal distinctiveness of short-term rental property design

The short-term rental market remains highly competitive, requiring that hosts should identify effective strategies to position their products for desirable performance. This study investigates the optimal balance beyond dyadic choice between differentiating from or conforming to competitors, in the dimensions of properties’ functional and aesthetic design. We hypothesize U-shaped distinctiveness-performance relationships considering high legitimacy pressure and low strategy effectiveness in the short-term rental context. Moreover, the moderating effects of factors including online review volume and listing age are examined. Analyzing a sample of 99,757 Airbnb listings in Texas, the findings reveal different patterns of product positioning between functionality and aesthetics. The moderate degree of distinctiveness in functionalities leads to the worst performance while in aesthetics generating the best outcome. This study contributes to the hospitality literature by introducing and testing optimal distinctiveness within the short-term rental market. The findings also provide positioning guidance for short-term rental listings under different conditions.

Price sensitivity and online shopping behavior during the COVID-19 pandemic

Purpose The COVID-19 pandemic has disrupted numerous businesses and upended the lives and shopping habits of most consumers. This study aims to examine the price sensitivity and the efficacy of online reviews during a pandemic crisis. Design/methodology/approach This study borrowed from the regulatory focus theory and heuristic-systematic model and used a unique longitudinal sample of 320,000 product/day observations from the jeans category, collected before and during the pandemic, to investigate how consumers’ online shopping behavior changed during the pandemic. Findings The results of several hierarchical linear modeling analyses revealed that during the pandemic consumers were less price-sensitive and more willing to pay price premiums for jeans. Furthermore, consumers were more (less) likely to be influenced by online review volume than valence. Finally, the results of a post-hoc study highlighted the potential role of regulatory focus as the underlying psychological mechanism explaining the effect of the pandemic. Originality/value This research contributes to the digital marketing and regulatory-focus literatures by showing that the COVID-19 pandemic may have triggered a prevention-focus state of mind and prompted consumers to place a greater value on online review volume than valence when shopping online (for jeans). Furthermore, this paper contributes to the pricing literature by offering further evidence that the pandemic may have inclined consumers to be less price-sensitive.

Online reviews and high-involvement product sales: Evidence from offline sales in the Chinese automobile industry

Online reviews are considered free sales assistance and play an important role in consumers’ purchasing decisions. Most research on the effect of online reviews on product sales has focused on low-involvement products, while research on the offline sales of high-involvement products is scarce. In this study, we collect the monthly sales data of 34 car models from January 2016-January 2020 and the online review data of Autohome’s platform to construct two two-way fixed effects models for analyzing the impact of online reviews on sales of high-involvement products. We also explore whether there is a non-linear relationship between online review valence and product sales, and how the interaction of review valence and volume affects product sales. The results show that there is an inverted U-shaped relationship between the valence of online reviews and the sales of high-involvement products. Moreover, the volume of online reviews has a significant positive impact on sales of high-involvement products, and an increase in the volume of online reviews boosts product sales. Furthermore, the valence of online reviews negatively moderates the relationship between the volume of online reviews and the sales of high-involvement products. The results of this study may help researchers to more fully understand the impact of online reviews on offline high-involvement product sales and provide guidance for managers to promote offline high-involvement products.

Some stay and some quit: Understanding P2P accommodation providers’ continuous sharing behavior from the perspective of feedback theory

Building on feedback theory, this study aims to understand providers' continuous sharing behavior (CSB) by integrating subjective and objective feedback in the context of peer-to-peer (P2P) accommodations. In Study 1, we test a mediation model by using survey data collected from 289 hosts of P2P accommodations. The results show that providers' positive feedback perception (PFP) is positively related to CSB and that intrinsic motivation mediates this effect. In Study 2, we collect 169 multisource data to explore the effect of objective online feedback on providers' PFP and subsequent effects in further detail. This study reveals that online ratings positively influence providers' PFP and that this effect is strengthened by the volume of online reviews. Further, we find sequential positive effects among providers’ PFP, intrinsic motivation, and CSB, which is consistent with Study 1. Implications for theory and practice are discussed.

Predictions on usefulness and popularity of online reviews: evidence from mobile phones for older adults

PurposeOnline reviews are regarded as a source of information for decision-making because of the abundance and ready availability of information. Whereas, the sheer volume of online reviews makes it hard for consumers, especially the older adults who perceive more difficulties in reading reviews and obtaining information compared to younger adults, to locate the useful ones. The main objective of this study is to propose an effective method to locate valuable reviews of mobile phones for older adults. Besides, the authors also want to explore what characteristics of the technology older adults prefer. This will benefit both e-retailers and e-commerce platforms.Design/methodology/approachAfter collecting online reviews related to mobile phones designed for older adults from a popular Chinese e-commerce platform (JD Mall), topic modeling, term frequency-inverse document frequency (TF-IDF), and linguistic inquiry and word count (LIWC) methods were applied to extract latent topics and uncover potential dimensions that consumers frequently referred to in their reviews. According to consumers' attitudes towards different popular topics, seven machine learning models were employed to predict the usefulness and popularity of online reviews due to their excellent performance in prediction. To improve the performance, a weighted model based on the two best-performing models was built and evaluated.FindingsBased on the TF-IDF, topic modeling, and LIWC methods, the authors find that older adults are more interested in the exterior, sound, and communication functions of mobile phones. Besides, the weighted model (Random Forest: Decision Tree = 2:1) is the best model for predicting the online review popularity, while random forest performs best in predicting the perceived usefulness of online reviews.Practical implicationsThis study’s findings can help e-commerce platforms and merchants identify the needs of the targeted consumers, predict reviews that will get more attention, and provide some early responses to some questions.Originality/valueThe results propose that older adults pay more attention to the mobile phones' exterior, sound, and communication function, guiding future research. Besides, this paper also enriches the current studies related to making predictions based on the information contained in the online reviews.

Initial Stage of the COVID-19 Pandemic: A Perspective on Health Risk Communications in the Restaurant Industry.

Restaurant online review websites have made changes to adapt to customers’ shifting needs during the COVID-19 crisis. Based on information behavior theory and social penetration theory, the present study investigated the changes in customers’ emotions and how the volume of online reviews as an indication of sales is impacted by the instructional (i.e., with quantitative variables) and emotional (i.e., with qualitative variables) information on review websites. By comparing the same month (January–April) during 2017–2020, positive sentiment experienced a plunge, while negative sentiment showed an upsurge in April 2020. The volume of reviews was impacted by five quantitative variables (i.e., confirmed COVID-19 case number, food delivery option, takeout option, delivery fee, and delivery time) and seven qualitative variables (i.e., anticipation, fear, trust, anger, disgust, joy, and sadness). This study provides new insight into understanding information content on review websites during the crisis (e.g., pandemic) from the perspective of health risk communication.

ONLINE CONSUMER REVIEW PADA CLUSTER GENERASI MILENIAL

This study purposed to identify the factors of online consumer reviews that effecting hotel booking intention of Millennials in Badung city. This research uses a quantitative approach. The sampling technique used was the Non-Probability Sampling method, namely purposive sampling with a total number of respondents are 385 respondents of Millennials in Badung city. The data analysis technique of this research was multiple linear regression analysis which was processed using the SPSS 21 program. The result showed a significantly positive relationship between the usefulness of online reviews, timelines of online reviews, and comprehensiveness of online reviews on respondents' hotel booking intentions. A positive but not significant relationship between the positive valence of online reviews on respondent's hotel booking intentions. While the impacts of the volume of online reviews and negative valence of online reviews upon hotel booking intentions were negative and not statistically significant

Exploring the effects of official-structured managerial responses on hotel online popularity

As a burgeoning mode of service management, online managerial response has become a critical aspect driving consumer online engagement and hotel performance improvement. Nevertheless, managerial response strategy, especially presentation style, is rarely studied. With a mixed method approach that includes the use of secondary data and experimental analyses, we investigate how the official-structured presentation style of managerial response affects the volume of online reviews and online ratings, which represent hotel online popularity, and the moderating effect of managerial response speed. Results indicate that 1) responding to consumers in the official-structured text increases the volume of online reviews, 2) responding to consumers in an official-structured style increases online ratings, and 3) response speed as an indicator of management effort enhances the effect of managerial response’s official-structured style on hotel popularity. Aside from expanding the literature on managerial response strategy and hospitality marketing, our findings also provide important implications for hospitality administrators and marketers.

Social media user-generated content, online search traffic and offline car sales

PurposeThis study explores the direct relationship between social media user-generated content (UGC), online search traffic and offline light vehicle sales of different models.Design/methodology/approachThe long-run equilibrium relationship and short-run dynamic effects between the valence and volume of UGC, online search traffic and offline car sales are analyzed by applying the autoregressive distribution lag (ARDL) model.FindingsThe study found the following. (1) In the long-run relationship, the valence of online reviews on social media platforms is significantly negatively correlated with the sales of all models. However, in the short-run, the valence of online reviews has a significant positive correlation with all models in different lag periods. (2) The volume of online reviews is significantly positively correlated with the sales of all models in the long run. However, in the short run, the relationship between the volume of online reviews and the sales of lower-sales-volume cars is uncertain. There is a significant positive correlation between the volume of reviews and the sales of higher-sales-volume cars. (3) Online search traffic has a significantly negative correlation with the sales of all models in the long run. However, in the short run, there is no consistent conclusion on the relationship between online search traffic and car sales.Originality/valueThis study provides a reference for managers to use in their efforts to improve offline high-involvement product sales using online information.

PENGARUH ONLINE REVIEW TERHADAP KEPUTUSAN MENGINAP DI JEJARING HOTEL LOKAL TERBESAR DI INDONESIA SANTIKA GRUP

The high internet usage in the country of Indonesia has made very significant changes in many ways, one of the very big changes in the habits of the Indonesian people who initially used booking activities more directly but now turn to using online ordering methods. This can benefit customers by making choices at online hotels on the internet. By developing it further, changing the pattern of hotel bookings today makes guests more careful in making reservations, guests can check the ratings of the hotel they will visit by just looking at the comments listed on the online review comments page of the online travel agent. The comments listed are made by previous guests who have enjoyed staying at this hotel so it is not uncommon that the comments listed determine the outcome of the stay decision. The study was conducted to analyze the interaction of its review dimensions, namely: the usefulness of online reviews, expertise reviews, timeliness of online reviews, online review volumes, online review valence (positive and negative), and completeness of online reviews on the decision to stay at the local Santika hotel Groups . The research method used is to discuss hypotheses developed based on related theories. Data were analyzed using multiple regression analysis. The results of this study found: The positive benefits of each dimension of useful online reviews, the expertise of reviewers, the timeliness of online reviews, positive online reviews, and the completeness of online reviews for stay results. There is a negative effect of online reviews on stay decisions, but there is no effect of online review volume on stay decisions.
 
 Keywords: Online review, Online Booking, Stay decision

HAS: Hybrid Analysis of Sentiments for the perspective of customer review summarization.

The reviews posted online by the end-users can help the business owners obtain a fair evaluation of their products/services and take the necessary steps. However, due to the large volume of online reviews being generated from time to time, it becomes challenging for business owners to track each review. The Customer Review Summarization (CRS) model that can present the summarized information and offer businesses with significant acumens to understand the reason behind customers' choices and behavior, would therefore be desirable. We propose the Hybrid Analysis of Sentiments (HAS) for the perspective of effective CRS in this paper. The HAS consists of steps like pre-processing, feature extraction, and review classification. The pre-processing phase removes the unwanted data from the text reviews using Natural Language Processing (NLP) based on different pre-processing functions. For efficient feature extraction, the hybrid mechanism consisting of aspect-related features and review-related features is proposed to build the unique feature vector for each customer review. Review classification is performed using different supervised classifiers like Support Vector Machine (SVM), Naïve Bayes, and Random Forest. The experimental results show that HAS efficiently performed the sentiment analysis and outperformed the existing state-of-the-art techniques with an F1 score of 92.2%.

Using Online Reviews for Customer Sentiment Analysis

Positive “word of mouth” is the key to successful innovation diffusion. Innovation managers pay close attention to examine customer sentiment. Online reviews are often the most accessible sources of customer feedback. Online review ratings and online review volume, the two most common metrics to interpret customer sentiment from online reviews, have some critical limitations. Online review ratings are prone to extremity bias since extremely satisfied or dissatisfied customers are most likely to leave online reviews. Online review volume can increase for any reason, and it does not necessarily indicate positive or negative customer feedback. This article explores text mining methods and proposes some alternative metrics to interpret customer sentiment. The findings show that sentiment scores might be less prone to extremity bias compared to online review ratings. Sentiment scores tended to fit a normal distribution while online review ratings were skewed to extreme values. Sentiment scores and review lengths, when combined, can provide a new angle to observe enthusiasm.

Examining Users’ Concerns while Using Mobile Learning Apps

<p class="0abstract">Mobile learning applications (apps) are increasingly and widely adopted for learning purposes and educational content delivery globally, especially with the massive means of accessing the internet done majorly on mobile handheld devices. Users often submit their feedback on use, experience and general satisfaction via the reviews and ratings given in the digital distribution platforms. With this massive information given through the reviews, it presents an opportunity to derives valuable insights which can be utilized for various reasons and by different stakeholders of these mobile learning apps. This large volume of online reviews creates significant information overload which presents a time-consuming task to read through all reviews. By combining text mining techniques of topic modeling using Latent Dirichlet Algorithm (LDA) and sentiment analysis using Linguistic Inquiry Word Count (LIWC), we analyze these user reviews. These techniques identify inherent topics in the reviews and identifies variables of user satisfaction of mobile learning apps. The thematic analysis done reveals different keywords which guide classification into the topics identified. Conclusively, the topics derived are important to app stakeholders for further modifications and evolution tasks.</p>

Effect of B&B host responses to online reviews on subsequent reviews: the moderating effects of class level

Entendiendo cómo las respuestas de los dueños de establecimientos de B&B a las opiniones de los turistas en línea promoverán las opiniones subsiguientes: Los efectos moderadores del nivel de clase de los establecimientos de B&BResumenPropósito -- Este estudio se centra en comprender cómo las características de las respuestas de los anfitriones de alojamientos B&B influyen en el rendimiento empresarial de volumen de reseñas; esto incluye el número de respuestas, la puntualidad de la respuesta y la duración de la misma.Metodología -- En primer lugar, el estudio construye un marco teórico para establecer un modelo de relación entre las características de las respuestas de los anfitriones de alojamientos, heterogéneos de alojamientos B&B y las revisiones posteriores. A continuación, el modelo es examinado por un modelo econométrico a partir de los datos recogidos en ctrip.com.Resultados -- Se ha demostrado que las respuestas rápidas y extensas a las reseñas en línea pueden aumentar potencialmente el número de reseñas posteriores, y tuvieron un mayor impacto en las viviendas de gran altura. La principal contribución teórica de este trabajo es construir un modelo para explicar cómo los múltiples factores de la respuesta de los anfitriones pueden afectar a su rendimiento empresarial y cómo estos efectos son moderados por las nivel de los alojamientos B&B, través de los datos reales de la prueba empírica.Implicaciones prácticas -- Proporciona una referencia para la práctica empresarial de los alojamientos B&B en línea, al informar sobre las implicaciones específicas de gestión para los anfitriones de alojamientos B&B. En el caso de las casas de alojamientos B&B de mayor nivel, con precios más altos y más reseñas en línea, se deberían dar más respuestas oportunas, ya que los turistas esperan de los anfitriones un servicio de atención al cliente más amable.Originalidad -- La investigación permite comprender el mecanismo de las respuestas de los anfitriones de alojamientos B&B en las reseñas posteriores. Sería el primer intento de demostrar el efecto moderador del precio y el volumen de las reseñas en línea sobre el impacto de las respuestas.

Shifting consumers’ sustainable behavior in the hospitality industry

Although research on hotel booking intention has been carried out in the last decade, the research that reveals the role of hotel reservation information through online consumer reviews in the millennial generation is still very rare. This study aims to determine the factors of online consumer reviews that affect hotel booking intentions for the millennial generation in Bali, Indonesia. This study uses a quantitative approach by distributing questionnaires to 385 respondents through a non-probability sampling technique, namely purposive sampling. The data analysis technique of this research is a multiple linear regression analysis processed using the SPSS 25.0 program. The results reveal that usefulness, timeline, and comprehensiveness have a significant effect on hotel booking intentions. Meanwhile, the volume of online reviews, the positive valence of online reviews, and the negative valence of online reviews are not significant for hotel booking intentions. The research findings reveal the characteristics of the millennial generation which are in line with the theory of reason action that they have their views in making decisions. The research implications are discussed in the paper.

Profiling reviewers’ social network strength and predicting the “Helpfulness” of online customer reviews

Abstract Online customer reviews have become a popular source of information that influences the purchasing decisions of many prospective customers. However, the rapidly increasing volume of online reviews presents a problem of information overload, which makes it difficult for customers to determine the quality of the reviews. This study defines the helpfulness of the reviews as a count variable and takes the review helpfulness prediction from both regression and classification perspectives. The influence of friends and followers on review helpfulness is examined by introducing Social Network Strength (SNS) features. Furthermore, the performance of Machine Learning (ML) algorithms and the importance of features are separately examined for both problems using different time span of reviews. The evaluation performed using a dataset of 90,671 Yelp shopping reviews demonstrates the effectiveness of the proposed approach. The findings of this study have important theoretical and practical implications for researchers, businesses, reviewers and review platforms.

Investigating the influence of regulatory focus on the efficacy of online review volume versus valence

Purpose Valence and volume of online reviews are generally considered to influence sales positively. However, existing findings regarding the relative influence of these two components have been inconclusive. This paper aims to explain some of these inconsistencies by examining the moderating role of regulatory focus (both as a chronic disposition and as a situational focus induced by the product category) in the relationship between online review volume/valence and consumers purchase decisions. Design/methodology/approach Two studies were conducted. Study 1 used a 2 (Volume: high/ low) * 3 (Valence: high/medium/low) within-subject experimental design. Study 2 analyzed real-world data from Amazon.com. Logistic and panel regression analyses were used to test the research hypotheses. Findings The studies confirmed the hypothesized effect of regulatory focus on online review valence and volume effects. Specifically, Study 1 showed that online review valence was more impactful for consumers with a promotion focus than for consumers with a prevention focus. The opposite was true for online review volume effects, where consumers with a prevention focus were influenced more by volume in their decision-making compared to consumers with a promotion focus. Study 2 showed that the pattern of results we found in Study 1 also applied to situational regulatory focus induced by the product category. The effect of review volume on sales rank was stronger for prevention-oriented products, whereas the effect of valence was stronger for promotion-oriented products. Research limitations/implications In Study 1, one product category was involved in the study (Digital camera). Involving more different product categories will add reliability to the results of current research. Also, it can offer external validity to current research results. In Study 2, there was no exact measurement for sales, as Amazon.com does not share that kind of information. Instead, Sales Rank was used as a proxy variable. Future research could look into the websites that offer access to the exact sales information. Practical implications The current research findings suggest the need for companies to adapt their consumer review management strategy to the regulatory orientation of their target market and products. When a promotion-focused mindset is targeted, strategies for increasing the favorability of product reviews should be used, in contrast, tactics for increasing the quantity of reviews may be more suitable when a prevention-focused mindset is involved. Originality/value To the best of the authors' knowledge, this research is the first to investigate the interaction between regulatory focus of consumers and products and online review components.

Differential Effects of the Valence and Volume of Online Reviews on Customer Share of Visits: The Case of US Casual Dining Restaurant Brands

Online customer reviews increasingly influence customer purchase decisions. Indeed, many customers have highlighted the significance of online reviews as an influential source of information. This study reports an investigation of the differential effects of online reviews, such as valence and volume, on the customer share of visits. Our findings suggest that valence (i.e., star rating) had more effect, giving a higher average check size to restaurants on the share of visits, while number reviews (volume) did not drive the share of visits to restaurants regardless of the average check size. Therefore, the ideal for casual dining restaurant brands would be to manage highly positive ratings to retain their customers.

온라인 리뷰가 매출에 미치는 영향력 분석: 텍스트기반 감성지수를 중심으로*

온라인 리뷰가 매출에 미치는 영향력 분석: 텍스트기반 감성지수를 중심으로*