Restaurant Ratings Research Articles

Understanding the online restaurant rating bias induced by air pollution and the underlying spatial and temporal effects

Using unique restaurant review data in the urban tourism system combined with air quality data in the Chinese context, we confirmed the air pollution-induced mood misattribution in terms of negative online restaurant rating bias. Further heterogeneity analyses grounded in expectancy-disconfirmation theory were conducted. Tests regarding air quality differences across geography (i.e. the spatial effect) show that good air quality in the city where a restaurant is located can induce a stronger online rating bias. Tourists, especially those who are from cities with poor air quality, tend to post biased online restaurant ratings on polluted days compared with their local peers. For locals, their online restaurant rating bias is additionally determined by air quality differences over time (i.e. the temporal effect), suggesting the significance of persistent air pollution rather than by air quality deterioration. Overall, our work highlights the importance of air pollution, an external environmental stimulus, in shaping consumers’ online rating bias towards restaurant services. This underscores the need for guidelines by regarding air pollution that inform sustainable urban planning and destination management.

AN ANALYTICS APPROACH TO STUDYING THE IMPACT OF ONLINE FOOD DELIVERY PARTNERS ON CUSTOMER SATISFACTION AT RESTAURANTS

The emergence of digital meal delivery platforms has completely changed the restaurant business and the way customers eat. This thesis looks into how online meal delivery partners affect restaurant patron satisfaction levels using an analytics-driven methodology. The studys objectives are to identify the critical elements that influence customer happiness and determine how delivery services affect a restaurants overall performance. The study technique makes use of a variety of datasets to conduct a multidimensional examination. The foundation of the analytical framework is made up of survey data on customer feedback. To enable thorough analysis, the data is carefully cleaned, integrated, and feature engineered. Through correlation analysis and predictive modelling techniques, the study scrutinizes the relationship between various parameters including delivery time, order accuracy, restaurant ratings, and customer satisfaction. Segmentation analysis is utilized to discern distinct customer preferences and behaviours, aiding in the identification of nuanced patterns. The findings unearth key insights into the factors that significantly influence customer satisfaction. The analysis unveils the impact of delivery partners on restaurant performance, delineating the critical facets that contribute to customer contentment in the context of online food delivery services. Leveraging analytics methodologies, we analyse various factors affecting customer satisfaction, including delivery time, order accuracy, customer service, and platform usability. The thesis culminates in actionable recommendations aimed at enhancing service quality and optimizing the delivery experience. The insights derived from the analytical study serve as a foundation for strategic enhancements, fostering collaborative improvements between restaurants and delivery partners. This research advances the understanding of the intricate dynamics between online food delivery services and customer satisfaction within the restaurant industry. It serves as a roadmap for restaurant owners, offering actionable strategies to elevate service standards and augment customer experiences in the evolving landscape of food delivery.

Determinants of Business Resilience in the Restaurant Industry During the COVID-19 Pandemic: A Textual Analytics Study on an O2O Platform Case

Understanding the resilience capabilities of restaurant operations and the determinants affecting these capabilities is critical to helping restaurants overcome the hardships owing to the coronavirus disease (COVID-19) pandemic. This article adopts a textual analytics approach to scientifically measure consumption trends and identify the shock to restaurant sales using online customer review data from Dianping.com (an O2O platform in China). Moreover, the article proposes a theoretical model of business resilience for the restaurant industry in the context of the pandemic. Then, an empirical investigation on how the determinants in our theoretical framework affect the resilience of restaurant business operations using the panel logit model is conducted. Our findings indicate that the pandemic has severely disrupted the full-service restaurants as compared to the quick-service restaurants. We identify four determinants of resilience, namely social capital (i.e., restaurant rating), physical capital (i.e., contactless service), economic capital (i.e., chain operation), and natural capital (e.g., location), which are significantly associated with the resilience of restaurant business during the pandemic. These four determinants play different roles in the resilience of full-service and quick-service restaurants. The findings of this study have theoretical contribution and generate some important managerial implications for helping the restaurant industry recover from disruptions brought by the COVID-19 pandemic.

Spatial differences and underlying mechanisms in electronic word of mouth in the foodservice industry: A case of Sanya, China.

Studying the electronic word-of-mouth (eWOM) in the foodservice industry can not only provide guidance for merchants, but also spatially optimize the urban foodservice industry, restaurants' location selection, and customers' purchasing decisions. In this study, taking Sanya city as the research object, using big data crawling technology to collect the directory and their attribute information of 2107 restaurants with more than 100 reviews. Kernel density analysis, grid analysis and the geographically weighted regression (GWR) model were applied to reveal the distribution characteristics and influencing factors of eWOM in the foodservice industry in Sanya, China. The main results are as follows. The foodservice industry in Sanya extends along the southern coastline and is characterized by little dispersion and agglomeration at the macro level. The overall eWOM score of the foodservice industry is low. Market popularity, restaurant rating, transportation conditions, and commercial development all have a positive impact on the eWOM of the foodservice industry. Population and price have both positive and negative effects and the public services has a nonsignificant impact on the eWOM. This study not only improves the theoretical understanding of the foodservice industry, but also provides a general reference for its development in other industries and cities.

The underestimated online clout of hotel location factors: spillover effect of online restaurant ratings on hotel ratings

ABSTRACT This study constructs a two-factor fixed effects model using monthly data from the Yelp open dataset spanning 2016 to 2021 to explore the effect of restaurants on hotel online ratings. Results reveal a positive spillover effect of online restaurant ratings on hotel ratings that diminishes with increasing distance between the restaurant and the hotel. Furthermore, although other restaurants’ higher average ratings can enhance hotel ratings, they may also dampen the positive influence of the target restaurant’s ratings on hotels. The findings mirror consumer perceptions of the link between hotels and restaurants and the significance of an integrated travel experience.

Enhanced Restaurant Rating Predictions: A Study of Linear and Ensemble Regression Methods

In this study, we investigate the application of various regression techniques to predict restaurant ratings based on a comprehensive Zomato dataset. The dataset encompasses 51,717 entries with features such as restaurant type, location, cuisine, and cost estimates. We employed four regression models: Linear Regression, CatBoost Regressor, Random Forest Regressor, and Decision Tree Regressor, to evaluate their performance in predicting ratings. The models were assessed using the R-squared (R²) metric to determine their effectiveness. The Random Forest Regressor achieved the highest R² score of 0.875, indicating its superior predictive capability. The CatBoost Regressor also performed well, demonstrating the effectiveness of gradient boosting methods. The study provides insights into the performance of various regression models and highlights the advantages of ensemble methods for accurate restaurant rating predictions.

‘BEST FOR FOODIES’: Food, Digital Media and Planetary Gentrification

AbstractLeisure activities, including place‐based food experiences, have become central to defining urban identities and branding places. Mobile and affluent urbanites’ search for authentic and cosmopolitan experiences is increasingly guided by corporate digital media such as apps and websites that direct them to previously ignored working‐class, ethnic and immigrant neighborhoods, which are being discursively and materially reconfigured to meet their needs, in turn causing the displacement of long‐time residents. We examine the relationship between food and gentrification through the lens of digital media, suggesting that they play an important role in shaping urban experiences and cities. Specifically, we investigate narratives produced by popular digital food media, not least websites and apps providing restaurant ratings and reviews, and their relationship to ongoing patterns of gentrification in Buenos Aires, Los Angeles and Paris. Using mixed methods that combine census data with ‘hybrid fieldwork’ in online and offline foodscapes, we identify some spatial patterns and key characteristics of food‐driven gentrification, highlighting the aestheticization of everyday life and its significance in encouraging and legitimizing planetary gentrification.

Price or quality? Consumers' preferences and willingness to pay (WTP) for online food delivery services in the COVID-19 era

PurposeThis article investigates the impact of the COVID-19 pandemic on the consumer preference for the attributes of online food delivery (OFD) services in India. It also shows how the order size influences the consumer's willingness to pay (WTP) for the attributes of OFD services.Design/methodology/approachThis work incorporates a conjoint analysis-based approach to determine the consumer preference for the attributes of OFDs such as price, delivery time, restaurant rating and packing quality during the COVID-19 pandemic. The fractional factorial design is applied for the data collection. The relative importance of the attributes and the part-worth utility of the attributes' levels have been determined. Further, the utility associated with the attributes' levels is used to find the consumer's WTP for different attributes.FindingsThe COVID-19 pandemic has changed consumer preference from price to food and packing quality in India. When the order is small, consumers exhibit a higher preference to the delivery time than packing quality. In contrast, consumers show a higher preference to packing quality than delivery time with the increase in order size. The consumer's WTP attains the highest level in case of food quality, followed by convenience and packing quality. The WTP for the attributes rises with the increase in order size.Practical implicationsThe insights highlight the need for the online food delivery industry to redesign the business framework in the post-pandemic era. The hygiene and safety measures maintained by the consumers during the pandemic have significantly changed their purchasing behaviour, raising their preference for service quality (food and packing quality) of the OFD services apart from price.Originality/valueThis work determines the consumers' utility for each attribute level of OFDs, along with their relative importance. Moreover, this study contributes to the existing literature by exhibiting the impact of the COVID-19 pandemic on the consumer preference and order size on consumer's WTP for the attributes.

Exploring user-generated content related to vegetarian customers in restaurants: An analysis of online reviews.

This study aimed to explore and evaluate factors that impact the dining experience of vegetarian consumers within a range of vegetarian-friendly restaurants. To explore the factors and understand consumer experience, this study analyzed a vast number of user-generated contents of vegetarian consumers, which have become vital sources of consumer experience information. This study utilized machine-learning techniques and traditional methods to examine 54,299 TripAdvisor reviews of approximately 1,008 vegetarian-friendly restaurants in London. The study identified 21 topics that represent a holistic opinion influencing the dining experience of vegetarian customers. The results suggested that "value" is the most popular topic and had the highest topic percentage. The results of regression analyses revealed that five topics had a significant impact on restaurant ratings, while 12 topics had negative impacts. Restaurant managers who pay close attention to vegetarian aspects may utilize the findings of this study to satisfy vegetarian consumer requirements better and enhance service operations.

Context-dependent choice and evaluation in real-world consumer behavior

A body of work spanning neuroscience, economics, and psychology indicates that decision-making is context-dependent, which means that the value of an option depends not only on the option in question, but also on the other options in the choice set—or the ‘context’. While context effects have been observed primarily in small-scale laboratory studies with tightly constrained, artificially constructed choice sets, it remains to be determined whether these context effects take hold in real-world choice problems, where choice sets are large and decisions driven by rich histories of direct experience. Here, we investigate whether valuations are context-dependent in real-world choice by analyzing a massive restaurant rating dataset as well as two independent replication datasets which provide complementary operationalizations of restaurant choice. We find that users make fewer ratings-maximizing choices in choice sets with higher-rated options—a hallmark of context-dependent choice—and that post-choice restaurant ratings also varied systematically with the ratings of unchosen restaurants. Furthermore, in a follow-up laboratory experiment using hypothetical choice sets matched to the real-world data, we find further support for the idea that subjective valuations of restaurants are scaled in accordance with the choice context, providing corroborating evidence for a general mechanistic-level account of these effects. Taken together, our results provide a potent demonstration of context-dependent choice in real-world choice settings, manifesting both in decisions and subjective valuation of options.

The Exploration of Restaurant Recommender System

The exploitation of Recommender Systems (RS) isstill a challenge, hence it is important to explore the three correlatedattributes, such as restaurant, food, and service ratings. Therefore, thisstudy provides an in-depth review of these attribute ratings using theCollaborative Filtering (CF) technique. Experiments were performed with k-NN,SVD, Slope One, and Co-Clustering algorithms, while RMSE, MSE, MAE, and FCPwere used as evaluation metrics. The results showed that the service restaurantrating predictions produced the best average MSE and RMSE accuracy in 5 and10-fold cross-validation. Furthermore, the best hyperparameter of algorithmsusing Grid Search was achieved in restaurant rating prediction. In conclusion,SVD surpasses other algorithms in MSE and RMSE for all scenarios.

Investigating the Methods of Restaurant Rating to Develop Halal Compliance Rating (HCR) Tool Within the Halal Certified Restaurants Globally

This paper reviews the weighted average approach of rating systems among the restaurant industries globally. Such review is crucial to developing Halal Compliance Rating (HCR) tool within the halal-certified restaurants in Malaysia as all as in other parts of the world. Halal-certified restaurants are in the Halal food and beverage (F&B) industry. At this moment, the Halal F&B industry does not have any standard rating method to rate the level of halal compliance practice of halal-certified restaurants. Hence, the objective of the study is to investigate the methods of restaurant rating globally and adopt the best-suited method to develop an HCR tool within halal-certified restaurants. Simultaneously, the study finds and recommends suitable linguistic and symbolic expressions for different ratings of halal compliance. To achieve the objectives, an extensive literature review was carried out. Additionally, to develop the HCR tool, the study used the ten components of halal compliance identified and weighted by Azam (2021). The findings show an example of using and calculating the HCR tool to rate the halal compliance of a restaurant and expressing the ratings linguistically and/or symbolically. Simultaneously, this paper justifies the use of the weighted average approach for rating halal-certified restaurants. Finally, it provides recommendations for future research to establish a standard HCR tool globally.

Managing minority opinions in large-scale group decision making based on community detection and group polarization

As the decision environment becomes increasingly complicated, the demand for large-scale group decision making (LSGDM) is increasing. Because of the differences in decision-makers’ (DMs’) personalities, knowledge, and experience, and incomplete information, irrational decision making behaviors, and minority opinion situation frequently appears. This study considers this phenomenon and proposes an LSGDM method by developing a similarity network of DMs on the basis of incomplete preference information. Moreover, the large number of DMs is divided into several clusters using a community detection model, and minority opinions are identified. To show the attitudes of DMs in different decision scenarios, the group polarization effects of individuals within communities are analyzed, and minority opinions using the family aggregation operators of the ordered weighted averaging operator are managed. Given the massive user involvement in online restaurant ratings, the recommendation list of Dianping.com is determined using the proposed LSGDM method. The results of the sensitivity and comparative analyses show that the LSGDM method is flexible and applicable because the attitude of DMs is considered.

A Peer-to-Peer Smart Food Delivery Platform Based on Smart Contract

The era of mobile information has arrived, and people’s lifestyles have undergone tremendous changes. Ordering takeaways through takeout apps on smartphones is one of them. However, most existing takeaway platforms charge high commissions in the middle. There are many fake reviews in restaurants, the authenticity of restaurant ratings is low, and the recommended dishes have low customer satisfaction. This paper aims to solve this problem by introducing a peer-to-peer architecture based on blockchain smart contracts. The proposed architecture leverages the automation of smart contracts to provide autonomous, commission-free food ordering and delivery services. In addition, the smart contract reward mechanism is used to collect order information and rating information, and a deep learning recommendation model is introduced to analyze the data to recommend restaurants and menus to the client accurately. To demonstrate the usability and efficiency of the proposed method, we conducted a case study using public chain-based technologies. At the same time, comprehensive evaluation experiments are carried out, and the results show the importance of the proposed food delivery system.

Recommendation System Algorithms on Location-Based Social Networks: Comparative Study

Currently, social networks allow individuals from all over the world to share ideas, activities, events, and interests over the Internet. Using location-based social networks (LBSNs), users can share their locations and location-related content, including images and reviews. Location rec-14 recommendation system-based LBSN has gained considerable attention in research using techniques and methods based on users’ geosocial activities. In this study, we present a comparative analysis of three matrix factorization (MF) algorithms, namely, singular value decomposition (SVD), singular value decomposition plus (SVD++), and nonnegative matrix factorization (NMF). The primary task of the implemented recommender system was to predict restaurant ratings for each user and make a recommendation based on this prediction. This experiment used two performance metrics for evaluation, namely, root mean square error (RMSE) and mean absolute error (MAE). The RMSEs confirmed the efficacy of SVD with a lower error rate, whereas SVD++ had a lower error rate in terms of MAE.

Food culture and online rating behavior

Culture has been confirmed to play an important role in the process of online word-of-mouth generation. To extend the knowledge of extant literature, we answer the question that whether food culture can influence tourist reviewers’ online rating behavior considering both the food culture in their residence and that in their destination. We find that tourist reviewers are more likely to give a lower online restaurant rating when they experience a food culture in the destination consistent with that in their residence. In addition, they tend to give more weight on the taste dimension than on the environment and service dimensions when they experience a food culture consistency. We also find that reviewers’ travel experience can strengthen the negative relationship between food culture consistency and online ratings. These findings have both theoretical and managerial implications.

Food Safety and Halal Issues in Food Aggregator Applications: “A Consumer's Point of View”

Food delivery services are developing significantly, especially during the COVID-19 pandemic. Food aggregator application is one of the online systems which enables customers to order delivery food from several food providers. This application was made as a simple app to make it easy to use by customers. In addition, it also makes it easier for food producers to sell their products. However, it has its limitation in which the consumers do not know the safety and halal status of the products offered in this application. This research aimed to understand the consumers' perceptions of the food's safety and halal status in this food delivery system. This descriptive-qualitative research was held in January - February in DIY through in-depth interviews using an online meeting platform. The results showed that the consumers believe that the products sold in the aggregator application are safe and halal. The consumer's choice and trust depended on the restaurant's rating, products' photos, and their taste. In the product's safety context, the consumers justified the product quality from its packaging. As for the halal label of the product, the consumers believe that the product is halal if there is no information that these products contain non-halal ingredients

Development of Taband restaurant rating scale utilizing mixed methods

Rating systems (RSs) are important for promotional efforts of service business and restaurants are not exceptions. However, current RSs are presumed to have some problems in transparency, objectivity, competence as well as in recognition. The purpose of this study is to design and develop a multidimensional restaurant rating scale, taking into account the shortcomings of elitist, democratic and academic/independent RSs. Using semi-structured face-to-face interviews with 12 restaurant experts and employing content analysis on the data, the Taband restaurant rating scale was developed. The reliability and validity of the scale was supported by exploratory factor analysis (EFA) (655 participants as first data set) and confirmatory factor analysis (CFA) (597 participants as second data set). The final version of the scale was composed of 42 items with 10 dimensions, and 20 new items were added to the restaurant rating literature via the present study.

The Disciplining Effect of Status: Evaluator Status Awards and Observed Gender Bias in Evaluations

We theorize that status awards will have a disciplining effect on evaluators, changing how they evaluate. Specifically, status awards will lead evaluators to place less weight on unreliable indicators of candidate quality, such as gender. We test this theory using data from restaurant evaluations on Yelp, focusing on the relationship between an evaluator’s restaurant rating and their reporting of being served by a man or a woman in their review text. We use Yelp’s evaluator status award (“Elite”) to analyze whether observed gender bias in the star ratings given to restaurants decreases after an evaluator receives this status award. We find that evaluators rate restaurants more similarly after receiving the award, regardless of whether they report being served by a man or a woman. Status awards in our context close the gender gap in restaurant ratings by 56.5% (a 0.07 stars improvement out of an initial rating gap of −0.13 stars). This reduction in gender bias is mostly due to a decrease in the number of extremely low (1 star) ratings in reviews that reference female servers. Research on status and evaluations has mostly focused on how evaluators react to increases in candidate status. We demonstrate the importance of evaluator status as a mechanism for decreasing observed gender differences in evaluations. This paper was accepted by Isabel Fernandez-Mateo, organizations.

A research on customer experiences and perceptions for Michelin starred restaurants

Michelin Guide is one of the well known world-recognized restaurant rating systems. This guide gives star symbols to restaurants that meet certain standards. Being a Michelin-starred restaurant in gastronomy sector is very important in terms of prestige. Having a star is becoming a factor that significantly affects customer potential as it means attesting to the flavour and ambience of restaurants. In this research, which measures consumers' perceptions of choosing Michelin restaurants, consumer reviews from Tripadvisor site were evaluated and to understand point of view of chefs and the managers a face to face interview conducted to 9 Michelin restaurants. The purpose of the study is to investigate the reasons that drive consumers to visit Michelin starred restaurants and to understand their perceptions. The research found that consumers are curious about Michelin restaurants, preferring to experience different titles such as food quality, hospitality, service and decoration from other restaurants. In addition, consumers who prefer Michelin restaurants evaluate the service as a whole, and the issues they care about come after the quality of the food.