Search

Despite evidence indicating the significant influence of online reviews on purchase decisions, even after considering a product's average rating (Vana and Lambrecht 2021), the underlying factors behind this effect and the broader impact of reviews on consumer decision making remain uncertain. This study uses clickstream data from a major online retailer to explore how negative reviews affect consumer search and purchase decisions. Leveraging exogenous variation created by the display of online reviews sorted by recency, the authors find that negative reviews significantly reduce a product's purchase probability because they (1) contrast with the often-high average product rating, (2) decrease the probability that consumers continue browsing for information about the focal product, (3) increase the probability of visiting the page of substitute products, and (4) increase the probability of viewing reviews about substitute products. Importantly, these effects apply to utilitarian products but not hedonic products and when reviews pertain to product functionality or customer service but not to taste-related factors. The authors estimate a product's vulnerability to negative reviews along two dimensions—purchase and search probability for substitutes—and display these effects on a two-dimensional map. [ABSTRACT FROM AUTHOR]

The recent surge in AI advancements, particularly generative AI, has grabbed the attention of major tech companies who are all striving to integrate it seamlessly into their products. This highlights the need to evaluate the various AI products on the market and identify the features that resonate most with users. SAS Enterprise Miner, a powerful text analysis tool, can be used to uncover hidden insights from user reviews. In this study, we will leverage various SAS functions to analyze reviews of different AI applications. By analyzing these reviews, we aim to pinpoint the unique strengths of these AI applications and propose improvements for existing ones. Furthermore, we hope to shed light on the potential social and economic impacts of these advancements based on our findings. [ABSTRACT FROM AUTHOR]

Homestays, which have emerged as a popular idea in the growing tourism industry, act as the most suitable alternative to encourage sustainable tourism activities in the Indian Himalayan Region (IHR). Homestay tourism not only provides economic benefits to rural communities but also promotes local art, architecture, traditions, and food habits. The objective of this study was to determine the distribution of homestays in the IHR and to evaluate and compare homestay management facilities between states; between rural and urban homestays; and based on reviews and ratings from previous guests. The study included all of IHR's states and union territories. The data for the number of homestays, ratings, and reviews of guests were taken from the popular travel booking sites with the help of a data extracting tool. According to the findings, Himachal Pradesh had the highest number of homestays (968), while Tripura had the least number of homestays (3), compared to all other states and union territories. The homestays in Jammu and Kashmir received the highest ratings. In Himachal Pradesh, homestays were available at a variety of pricing points, ranging from 300 to 38,000 INR a night. Overall, it was observed that rural homestays were equally good as their counterparts in urban areas when the hospitality standards of the rural and urban homestays were compared. To boost the effectiveness of this programme in IHR, the study's findings may be used to design local policies, rules, and incentive programmes for the areas in which they will be put into practise. [ABSTRACT FROM AUTHOR]

This research adopts a holistic approach to analyze customer reviews in the e-commerce industry by utilizing a combined approach of numerical and text analysis. Specifically, this study integrates univariate, multivariate, and sentiment analysis to gain comprehensive insights into product preferences and customer satisfaction. The methodology includes a detailed examination of univariate distributions to uncover numerical trends in product ratings and preferences. Multivariate distributions are explored to understand the complex relationships between related variables. Sentiment analysis is performed using the Sentiment Intensity Analyzer to categorize reviews into positive, neutral, and negative sentiments. Additionally, N-gram analysis is applied to both recommended and non-recommended reviews to identify key themes, such as dissatisfaction with product size and satisfaction with fit. Logistic regression and naive Bayes models are employed to classify sentiment, with logistic regression achieving high accuracy on both training (91.3%) and validation data (89.2%). This research highlights the significant role of product recommendations as indicators of positive sentiment, while product ratings reveal the complexity in consumer judgment. The study contributes significantly to understanding the dynamics of customer reviews in the e-commerce industry, providing a solid foundation for smarter decision-making to improve customer experience and product quality. [ABSTRACT FROM AUTHOR]

The unprecedented production and sharing of data, opinions, and comments among people on social media and the Internet in general has highlighted sentiment analysis (SA) as a key machine learning approach in scientific and market research. Sentiment analysis can extract sentiments and opinions from user-generated text, providing useful evidence for new product decision-making and effective customer relationship management. However, there are concerns about existing standard sentiment analysis tools regarding the generation of inaccurate sentiment classification results. The objective of this paper is to determine the efficiency of off-the-shelf sentiment analysis APIs in recognizing low-resource languages, such as Greek. Specifically, we examined whether sentiment analysis performed on 300 online ordering customer reviews using the Meaning Cloud web-based tool produced meaningful results with high accuracy. According to the results of this study, we found low agreement between the web-based and the actual raters in the food delivery services related data. However, the low accuracy of the results highlights the need for specialized sentiment analysis tools capable of recognizing only one low-resource language. Finally, the results highlight the necessity of developing specialized lexicons tailored not only to a specific language but also to a particular field, such as a specific type of restaurant or shop. [ABSTRACT FROM AUTHOR]

Motivated by applications in text mining and discrete distribution inference, we test for equality of probability mass functions of K groups of high-dimensional multinomial distributions. Special cases of this problem include global testing for topic models, two-sample testing in authorship attribution, and closeness testing for discrete distributions. A test statistic, which is shown to have an asymptotic standard normal distribution under the null hypothesis, is proposed. This parameter-free limiting null distribution holds true without requiring identical multinomial parameters within each group or equal group sizes. The optimal detection boundary for this testing problem is established, and the proposed test is shown to achieve this optimal detection boundary across the entire parameter space of interest. The proposed method is demonstrated in simulation studies and applied to analyse two real-world datasets to examine, respectively, variation among customer reviews of Amazon movies and the diversity of statistical paper abstracts. [ABSTRACT FROM AUTHOR]

Bilateral ratings on online marketplaces may soften price competition and sellers of higher quality may charge lower prices. Abstract. Peer-to-peer (P2P) markets have become a critical aspect of the modern economy. We consider a P2P market in which a time-sensitive service is provided through a platform that matches providers of varying qualities to customers of varying costs. The P2P platform features bilateral ratings, which distinguish it from a traditional market: ratings of a provider reveal the provider's service quality and ratings of a customer reveal the customer's service cost. The existence of a cost measure in the P2P market leads to novel pricing considerations: a provider can attract low-cost customers by charging a low price, leading to an endogenous composition effect. As a result, equilibrium prices may decrease as customers become more costly to serve or as the platform's commission rate gets higher. Under certain conditions, high-quality providers may even charge a lower equilibrium price than low-quality providers in order to cherry-pick low-cost customers. Exploratory analysis reveals that, compared with unilateral ratings, bilateral ratings may soften provider competition and raise equilibrium prices as the providers target customers in different cost segments. History: Anthony Dukes served as the senior editor. Funding: This work was supported by the NET Institute (summer research fund). Supplemental Material: The online appendix is available at https://doi.org/10.1287/mksc.2022.0158. [ABSTRACT FROM AUTHOR]

The unprecedented production and sharing of data, opinions, and comments among people on social media and the Internet in general has highlighted sentiment analysis (SA) as a key machine learning approach in scientific and market research. Sentiment analysis can extract sentiments and opinions from user-generated text, providing useful evidence for new product decision-making and effective customer relationship management. However, there are concerns about existing standard sentiment analysis tools regarding the generation of inaccurate sentiment classification results. The objective of this paper is to determine the efficiency of off-the-shelf sentiment analysis APIs in recognizing low-resource languages, such as Greek. Specifically, we examined whether sentiment analysis performed on 300 online ordering customer reviews using the Meaning Cloud web-based tool produced meaningful results with high accuracy. According to the results of this study, we found low agreement between the web-based and the actual raters in the food delivery services related data. However, the low accuracy of the results highlights the need for specialized sentiment analysis tools capable of recognizing only one low-resource language. Finally, the results highlight the necessity of developing specialized lexicons tailored not only to a specific language but also to a particular field, such as a specific type of restaurant or shop.

Customer reviews are the second-most reliable source of information, followed by family and friend referrals. However, there are many existing customer reviews. Some online shopping platforms address this issue by ranking customer reviews according to their usefulness. However, we propose an alternative method to rank customer reviews, given that this system is easily manipulable. This study aims to create a ranking model for reviews based on their usefulness by combining product and seller service aspects from customer reviews. This methodology consists of six primary steps: data collection and preprocessing, aspect extraction and sentiment analysis, followed by constructing a regression model using random forest regression, and the review ranking process. The results demonstrate that the ranking model with service considerations outperformed the model without service considerations. This demonstrates the model's superiority in the three tests, which include a comparison of the regression results, the aggregate helpfulness ratio, and the matching score. [ABSTRACT FROM AUTHOR]

Copyright of Techno.com is the property of Universitas Dian Nuswantoro, Fakultas Ilmu Komputer and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This research adopts a holistic approach to analyze customer reviews in the e-commerce industry by utilizing a combined approach of numerical and text analysis. Specifically, this study integrates univariate, multivariate, and sentiment analysis to gain comprehensive insights into product preferences and customer satisfaction. The methodology includes a detailed examination of univariate distributions to uncover numerical trends in product ratings and preferences. Multivariate distributions are explored to understand the complex relationships between related variables. Sentiment analysis is performed using the Sentiment Intensity Analyzer to categorize reviews into positive, neutral, and negative sentiments. Additionally, N-gram analysis is applied to both recommended and non-recommended reviews to identify key themes, such as dissatisfaction with product size and satisfaction with fit. Logistic regression and naive Bayes models are employed to classify sentiment, with logistic regression achieving high accuracy on both training (91.3%) and validation data (89.2%). This research highlights the significant role of product recommendations as indicators of positive sentiment, while product ratings reveal the complexity in consumer judgment. The study contributes significantly to understanding the dynamics of customer reviews in the e-commerce industry, providing a solid foundation for smarter decision-making to improve customer experience and product quality.

User feedback in text classification serves multiple purposes, including refining models, enhancing datasets, adapting to user preferences, identifying emerging topics, and evaluating system performance, all of which contribute to the creation of more effective and user-centric classification systems. Many text classification techniques, including data mining, machine learning, and deep learning approaches, have been employed in previous literature, each making significant contributions to the field. This paper aims to contribute by guiding researchers seeking commonly used classification techniques and evaluation metrics in text processing. Additionally, it identifies the classification technique that generates higher accuracy and works as a basis for researchers to synthesize studies within their respective fields. Preferred reporting items for systematic reviews and meta-analysis (PRISMA) methodology is adapted to systematically review 28 current literatures on text classification on user feedback. The results obtained are guided by four research questions; paper distribution year, dataset source and size; evaluation metric and model accuracy. The review has shown that support vector machines (SVM) are frequently employed and consistently achieve high levels of accuracy as high as 97.17% with various datasets used. The future direction of this work could explore models that integrate sentiment analysis and natural language understanding to more accurately capture nuanced user opinions and preferences. [ABSTRACT FROM AUTHOR]

Abstract Background The importance of customer reviews in determining satisfaction has significantly increased in the digital marketplace. Using sentiment analysis in customer reviews has immense potential but encounters challenges owing to domain heterogeneity. The sentiment orientation of words varies by domain; however, comprehending domain-specific sentiment reviews remains a significant constraint. Aim This study proposes an Improved VADER (IVADER) lexicon-based classification model to evaluate customer sentiment in multiple domains. The model involves constructing a domain-specific dictionary based on the VADER lexicon and classifying doeviews using the constructed dictionary. Methodology The proposed IVADER model uses data preprocessing, Vectorizer transformation, WordnetLemmatizer-based feature selection, and enhanced VADER Lexicon classifier. Result Compared to existing studies, the IVVADER model accomplished outcomes of accuracy of 98.64%, precision of 97%, recall of 94%, f1-measure of 92%, and less training time of 44 s for classification. Outcome Product designers and business organizations can benefit from the IVADER model to evaluate multi-domain customer sentiment and introduce new products in the competitive online marketplace.

Aspect extraction is the most important factor influencing the quality of Aspect-Based Sentiment Analysis (ABSA). Aspect extractions are divided into three approaches: supervised, unsupervised, and hybrid methods. Most previous aspect extraction algorithms focus on the explicit aspect, which lacks meaningful ABSA. Thus, considering the implicit aspect has become significant as most customer reviews consist of these by about 30%. Hybrid approaches have attempted to solve both aspects by integrating the frequency-based approaches (FB) with syntax, hybrid Conditional Random Field (CRF) with syntax, and hybrid FB with CRF, but the performance is still low. Extracting the implicit and compound noun aspects is challenging due to their hidden nature and special syntax needs. The implicit aspect needs FB, syntax dependency, and specialized tagging with feature embedding using natural language processing (NLP) solution, while the compound noun aspect needs FB, syntax dependency-based NLP solving. Therefore, this paper proposes a noble hybrid method combining frequency-based, syntax-based dependency, and CRF algorithms using tagging and labeling to extract both implicit and explicit aspects. It also provides a mechanism for extracting and calculating implicit and explicit aspects and a method for accurately identifying compound noun aspects. Experiments with the benchmark SemEval and Amazon review dataset validate the suggested hybrid model’s effectiveness. The proposed method produced remarkable improvement in extracting explicit and implicit aspects and improved overall results with precision-recall and accuracy between 5-15 percent. Moreover, this study has shown the number and the list of explicit and implicit aspects. The proposed method has obtained (2269, 368), (523, 60), (322, 55) number of explicit versus implicit aspects for SemEval 16, Amazon (Canon), and Amazon (Nokia) datasets, respectively. Hybrid with frequency-based, CRF’s superiority tagging and syntax help solve implicit and explicit aspects, including compound nouns.

Annotation and analysis of online customer reviews were identified as significant problems in various domains, including business intelligence, marketing, and e-governance. In the last decade, various approaches based on topic modeling have been developed to solve this problem. The known solutions, however, often only work well on content with static topics. As a result, it is challenging to analyze customer reviews that include dynamic and constantly expanding collections of short and noisy texts. A method was proposed to handle such dynamic content. The proposed system applied a dynamic topic model using BERTopic to monitor topics and word evolution over time. It would help decide when the topic model needs to be retrained to capture emerging topics. Several experiments were conducted to test the practicality and effectiveness of the proposed framework. It demonstrated how a dynamic topic model could handle the emergence of new and over-time-correlated topics in customer review data. As a result, improved performance was achieved compared to the baseline static topic model, with 25% of new segmented texts discovered using the dynamic topic model. Experimental results have, therefore, convincingly demonstrated that the proposed framework can be used in practice to develop automatic review annotation tools.

This study aims to contribute to the limited empirical evidence on Automated Taxis (ATs) by analysing the in-vehicle features that ATs ought to have to satisfy taxi passengers requests that in a Normal Taxi (NT) are dealt with a direct communication between the passenger and the driver. Based on the results of focus groups and several pilots, two in-vehicle features are tested: change of destination and chat with an operator during the trip. The paper also contributes to the body of literature on the impact of social influence on the adoption of innovation by testing the impact of consumer reviews other than the typical measure of adoption and injunctive norms. A Stated Choice (SC) experiment was built putting particular effort in the definition and presentation of the new attributes tested. The study was applied in China among current users of NTs (i.e. with the driver). Hybrid choice models were estimated and a resampling technique was used to test the model sensitivity to the sample gathered. Results show that on average, Chinese taxi users are willing to pay 0.35 Euros to have the option to 'change the destination' and 0.78 Euros to be able to 'chat with an operator' inside the AT. Among the social influence attributes, the reviews from previous customers confirmed to be the most effective measure, users are willing to pay 1.58 Euros more to use a taxi that got good reviews for long trips (≥ 30 min) and 0.57 Euros for shorter trips. The Willingness to Pay (WTP) estimated are all significant at more than 95% and have a narrow confidence intervals. [ABSTRACT FROM AUTHOR]

Background: The importance of customer reviews in determining satisfaction has significantly increased in the digital marketplace. Using sentiment analysis in customer reviews has immense potential but encounters challenges owing to domain heterogeneity. The sentiment orientation of words varies by domain; however, comprehending domain-specific sentiment reviews remains a significant constraint. Aim: This study proposes an Improved VADER (IVADER) lexicon-based classification model to evaluate customer sentiment in multiple domains. The model involves constructing a domain-specific dictionary based on the VADER lexicon and classifying doeviews using the constructed dictionary. Methodology: The proposed IVADER model uses data preprocessing, Vectorizer transformation, WordnetLemmatizer-based feature selection, and enhanced VADER Lexicon classifier. Result: Compared to existing studies, the IVVADER model accomplished outcomes of accuracy of 98.64%, precision of 97%, recall of 94%, f1-measure of 92%, and less training time of 44 s for classification. Outcome: Product designers and business organizations can benefit from the IVADER model to evaluate multi-domain customer sentiment and introduce new products in the competitive online marketplace. [ABSTRACT FROM AUTHOR]

This research highlights the importance of brand image management and customer reviews in influencing trust and purchasing behavior on the Shopee Marketplace platform. Research findings confirm that effective brand image management and positive customer reviews have a significant impact on customer trust in a product or brand. This emphasizes the importance of building a strong brand image through the right marketing strategies and responding well to customer reviews. Customer trust is identified as a key factor in influencing purchasing decisions, with companies and sellers needing to focus on building and maintaining trust through quality products, good customer service, and positive brand reputation management. In a competitive e-commerce environment, good brand image management and positive customer reviews have become important aspects in attracting customer interest and influencing purchasing decisions. Therefore, a successful marketing strategy must include efforts to build and maintain customer trust through consistency of experience, product quality, and response to customer reviews. Thus, this research highlights the need for companies and sellers on Shopee to manage and respond to customer reviews well to build a positive brand image and increase customer trust in the e-commerce context.

Problem definition: Customer reviews are essential to online marketplaces. However, reviews typically vary; ratings of a product or service are rarely the same. In many service marketplaces, including the ones for solar panel installations, supply-side participants are active. That is, a seller must make a proposal to serve each customer. In such marketplaces, it is not clear how (or if) the dispersion in customer reviews affects the seller activity level and number of matches in the marketplace. Our paper examines this by considering both ratings and text reviews. To our knowledge, this is the first paper that empirically studies how the review dispersion affects a seller's activity level and the number of matches in an online marketplace with active sellers. Distinct from literature, we examine the relationship between the review dispersion and supply-side activities in an online service marketplace. Methodology/results: We collaborated with one of the largest online solar marketplaces in the United States that connects potential solar panel adopters with installers. We obtained a unique data set from the marketplace for 2013 − 2018. We complement this with public data sets. Our analysis uses traditional econometrics methods, a clustering method, and the deep-learning-based natural-language-processing model BERT developed by Google AI. We find that the dispersion in customer reviews has a significant and inverted U-shaped relationship with an installer's marketplace activity level. Intuitively, a marketplace operator would favor having more sellers with perfect ratings. In contrast, we identify a significant and inverted U-shaped relationship between the market-level review dispersion and transactions. Managerial implications: Our paper provides key insights to marketplace operators and sellers. We find that in contrast to general belief, an operator can improve its market transactions by keeping/promoting sellers with low ratings or avoiding (negative) review filtering. Furthermore, sellers' implementation of "rating gating" to avoid negative reviews may backfire for them by reducing their matches. Supplemental Material: The e-companion is available at https://doi.org/10.1287/msom.2021.0104. [ABSTRACT FROM AUTHOR]

Customer reviews are valuable resources containing customer opinions and sentiments toward the product. The reviews are informative but can be quite lengthy or may contain repetitive information calling for opinion summarization systems that retain only the significant opinion information from the review. Abstractive summarization is a form of text summarization that generates a summary mimicking a human-written summary [1]. When pretrained language models are finetuned for abstractive review summarization, there usually occurs a problem known as the ‘domain shift’, because the source and target domains exhibit data from varying distributions [2]. This issue results in performance degradation of the model at the target end. This paper contributes a data package comprising of an annotated abstractive summarization dataset (annotated_abs_summ) of airline reviews having 500 reviews and abstractive summary pairs, a dataset (review_titles_data) consisting of 7079 reviews and review title pairs for review title generatioon or domain adaptive training [3] to address the domain shift problem for abstractive opinion summarization and, an annotated reviews dataset (annotated_sentiment) for rating-based sentiment classification. All datasets have been collected from the Skytrax Review Portal via web scraping using Python programming language. The datasets have several potential use cases. The abstractive summarization dataset can serve as a benchmark dataset for airline review summarization. The dataset for domain adaptive training can be used as a standalone dataset for review title generation. The dataset for sentiment analysis is multipurpose having columns like user rating and recommendation value, that can be used for statistical analysis like finding correlation between these data items as well as for other Natural Language Processing (NLP) tasks like predicting rating or recommendation value from the customer reviews. The datasets can be extended using various data augmentation techniques [4,5]. Moreover, the datasets are related and can be collectively used to develop a multi-task learning model [6] for better learning efficiency and improved performance.

Customer reviews are a new type of third-party evaluation that has transformed how power operates over evaluated producers, and in so doing has attracted scholarly attention. However, this literature rarely addresses the power relationships operating between platforms collecting and aggregating these reviews. We address this blind spot by relying on Pierre Bourdieu's theory of fields, which we use to highlight that the reaction of producers to traditional third-party evaluations depend on, and reproduce, the domination of an evaluation intermediary over its competitors. Our qualitative study of the field of jobbing platforms in France reveals that producers react to customer reviews only on platforms accumulating relatively better stocks of reviews, in a self-reinforcing manner. Managers of platforms with smaller stocks of reviews resist by sheltering jobbers from reviews. Our study re-introduces field-level power dynamics between platforms to research exploring the forms of power that operate on producers subjected to reviews. It adds to studies of evaluation intermediaries by specifying that the accumulation of reviews underpins the power relationships between intermediaries in the customer review era and by identifying sheltering as a new form of resistance. Finally, it updates Bourdieu's theory for the digital age by explaining that individuals' accumulation of capital online relates to inter-organisational power dynamics. [ABSTRACT FROM AUTHOR]

Machine learning frameworks categorizing customer reviews on online products have significantly improved sales and product quality for major manufacturers. Manually scrutinizing extensive customer reviews is imprecise and time-consuming. Current product research techniques rely on text mining, neglecting audio, and image components, resulting in less productive outcomes for researchers and developers. AI-based machine learning frameworks that consider social media and online buyer reviews are essential for accurate recommendations in online e-commerce shops. This research paper proposes a novel machine-learning-based framework for categorizing customer reviews that uses a bag-of-features approach for feature extraction and a hybrid DNN framework for robust classification. We assess the performance of our machine learning framework using AliExpress and Amazon e-commerce product review data provided by customers, and we have achieved a classification accuracy of 91.5% with only 8.46% fallout. Moreover, when compared with state-of-the-art models, our proposed model shows superior performance in terms of sensitivity, specificity, precision, fallout, and accuracy. [ABSTRACT FROM AUTHOR]

Nowadays, commercial transactions and customer reviews are part of human life and various business applications. The technologies create a great impact on online user reviews and activities, affecting the business process. Customer reviews and ratings are more helpful to the new customer to purchase the product, but the fake reviews completely affect the business. The traditional systems consume maximum time and create complexity while analyzing a large volume of customer information. Therefore, in this work optimized recommendation system is developed for analyzing customer reviews with minimum complexity. Here, Amazon Product Kaggle dataset information is utilized for investigating the customer review. The collected information is analyzed and processed by batch normalized capsule networks (NCN). The network explores the user reviews according to product details, time, price purchasing factors, etc., ensuring product quality and ratings. Then effective recommendation system is developed using a butterfly optimized matrix factorization filtering approach. Then the system's efficiency is evaluated using the Rand Index, Dunn index, accuracy, and error rate. [ABSTRACT FROM AUTHOR]

With the recent expansion of social media in the form of social networks, online portals, and microblogs, users have generated a vast number of opinions, reviews, ratings, and feedback. Businesses, governments, and individuals benefit greatly from this information. While this information is intended to be informative, a large portion of it necessitates the use of text mining and sentiment analysis models. It is a matter of concern that reviews on social media lack text context semantics. A model for sentiment classification for customer reviews based on manifold dimensions and manifold modeling is presented to fully exploit the sentiment data provided in reviews and handle the issue of the absence of text context semantics. This paper uses a deep learning framework to model review texts using two dimensions of language texts and ideogrammatic icons and three levels of documents, sentences, and words for a text context semantic analysis review that enhances the precision of the sentiment categorization process. Observations from the experiments show that the proposed model outperforms the current sentiment categorization techniques by more than 8.86%, with an average accuracy rate of 97.30%. [ABSTRACT FROM AUTHOR]

Nowadays, opinion mining is becoming a trending research topic. The existing opinion mining detection schemes were used to determine the status of product's performance, wherein information is disseminated (positive or negative), even though the existing methods did not provide high accuracy and also increase the computational complexity and computation time. To overcome these issues, a deep non-linear and unbiased deep decisive pooling (N-UDDP) learning is proposed in this paper for getting accurate opinion mining of customer review. Initially, the customer reviews are taken from Amazon dataset. Then, the customer reviews are given as input to N-UDDP learning for getting accurate opinion mining of customer review. The proposed N-UDDP learning contains skip-gram input layer, non-linear ReLU-enabled activation function layer, and unbiased decisive pooling layer. The skip-gram input layer is utilized to obtain the computationally efficient features from input customer review. The non-linear ReLU-enabled activation function layer is used to obtain the unique and relevant features through eigenvector generation. Finally, the mining accuracy can be improved via unbiased decisive pooling layer by explicitly incorporating their confidence over the pooling function through decisive rules. Initially, the customer reviews are taken from Amazon dataset. Then, the customer reviews are given as input to N-UDDP learning for getting accurate opinion mining of customer review. The proposed N-UDDP learning contains skip-gram input layer, non-linear ReLU-enabled activation function layer, and unbiased decisive pooling layer. The skip-gram input layer is utilized to obtain the computationally efficient features from input customer review. The non-linear ReLU-enabled activation function layer is used to obtain the unique and relevant features through eigenvector generation. Finally, the mining accuracy can be improved via unbiased decisive pooling layer by explicitly incorporating their confidence over the pooling function through decisive rules. The proposed N-UDDP method attains 10.99%, 44.83%, 17.53%, 11.93%, 11.19%, 53.96%, and 13.285% higher accuracy than the existing methods, like ontology-driven feature engineering, multi-task learning framework, CNN-RNN, NA-DLSTM, MLP, autoencoder, and MV-DNN. The proposed N-UDDP method shows better accuracy by reducing the computational time and overhead. [ABSTRACT FROM AUTHOR]

Most people in industrialized countries regularly purchase products online. Consumers often rely on previous customers’ reviews to make purchasing decisions. The current research investigates whether potential online customers select these reviews in a biased way and whether typical interface properties of product evaluation portals foster biased selection. Based on selective exposure research, potential online customers should have a bias towards selecting positive reviews when they have an initial preference for a product. We tested this prediction across five studies (total N = 1376) while manipulating several typical properties of the review selection interface that should – according to earlier findings – facilitate biased selection. Across all studies, we found some evidence for a bias in favor of selecting positive reviews, but the aggregated effect was non-significant in an internal meta-analysis. Contrary to our hypothesis and not replicating previous research, none of the interface properties that were assumed to increase biased selection led to the predicted effects. Overall, the current research suggests that biased information selection, which has regularly been found in many other contexts, only plays a minor role in online review selection. Thus, there is no need to fear that product evaluation portals elicit biased impressions about products among consumers due to selective exposure.

Online reviews influence customer decisions and present publicly available data to investigate differences between customer evaluations for local and chain businesses. We conduct a text analysis on a sample of 80,728 online customer reviews of quick-service restaurants to examine how the impact of dining experience attributes on customer evaluation differs between the two restaurant types. Estimation of multilevel multinomial models reveals that customer reviews for local restaurants have less polarized sentiment than chain restaurants. This polarization is also evident for sentiment usage related to four dining experience attributes: food, service, ambience, and price. Although food offerings are essential to get high ratings for local restaurants, service quality has a relatively greater impact on customer satisfaction for chains. Although customer reviews favor local restaurants, they need powerful testimonials for differentiation due to high review valence among their local competitors. [ABSTRACT FROM AUTHOR]

The current paper discusses the topic of business to consumer interaction in the post COVID era. It briefly reviews key literature on aspects related to business communication practices and trends, and analyses a corpus of customer reviews selected from leading online e-commerce sites to see how customers interact with service/product providers to express satisfaction and dissatisfaction. The analysis will try to identify how the language used reflects the relation between participants, their credibility or lack of credibility in front of each other, and whether such aspects may be said to influence online sales trends. [ABSTRACT FROM AUTHOR]

Copyright of International Journal of Global Tourism Research / Uluslararası Global turizm Araştırmaları Dergisi is the property of International Journal of Global Tourism Research and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Perception of customer requirements and intention is crucial for product redesign where customer reviews play a significant role. Customers dynamically make decision and interact with others, which lead to the evolution of customer reviews. A customer reviews evolution model (CREM) is proposed to analyse the dynamic evolution process of group customer reviews by using a modified Deffuant-Weisbuch model based on opinion dynamics. In the proposed methodology, negativity bias and the helpfulness of reviews are incorporated according to the characteristics of customers and reality. Based on the related literature reviews and survey, negativity bias is introduced to present that positive customers are still sensitive to negative reviews out of confidence radius and will interact with them. In addition, the helpfulness of reviews is used to reflect the rate of information acquisition since the ability of expression varies from person to person. Moreover, as a case study, the customer reviews evolution of a smartphone is modelled to support the redesigned attributes evaluation. Finally, the feasibility and effectiveness of the proposed CREM is expounded through result analysis and discussion. [ABSTRACT FROM AUTHOR]