Relationship between customer sentiment and online customer ratings for hotels - An empirical analysis

This study aims to establish a relationship between customer sentiments in online reviews and customer ratings for hotels. Customer sentiment refers to the emotions expressed by customers through the text reviews. These sentiments can be positive, negative or neutral. The study explores customer sentiments and expresses them in terms of customer sentiment polarity. Our results find consistency between customer ratings and actual customer feelings across hotels belonging to the two categories of premium and budget. Customer sentiment polarity explains significant variation in customer ratings across both the hotel categories. With regard to managerial implications, the study finds that, when compared with premium hotels, managers of budget hotels should improve their staff performance and hotel services. The present study is not exhaustive and other factors like customer review length and review title sentiment can be analyzed for their effects on customer ratings.     

Restaurant survival prediction using customer-generated content: An aspect-based sentiment analysis of online reviews

Business failure prediction or survival analysis can assist corporate organizations in better understanding their performance and improving decision making. Based on aspect-based sentiment analysis (ABSA), this study investigates the effect of customer-generated content (i.e., online reviews) in predicting restaurant survival using datasets for restaurants in two world famous tourism destinations in the United States. ABSA divides the overall review sentiment of each online review into five categories, namely location, tastiness, price, service, and atmosphere. By employing the machine learning–based conditional survival forest model, empirical results show that compared with overall review sentiment, aspect-based sentiment for various factors can improve the prediction performance of restaurant survival. Based on feature importance analysis, this study also highlights the effects of different types of aspect sentiment on restaurant survival prediction to identify which features of online reviews are optimal indicators of restaurant survival.     

Drivers of helpfulness of online hotel reviews: A sentiment and emotion mining approach

Although online hotel reviews (OHR) help consumers in better decision–making, and service providers in better service design and delivery, they are hard to manage due to their high volume, velocity, and veracity. This paper focuses on the drivers of helpfulness of textual OHR, for which we have used text-mining techniques to find the sentiment content, polarity, and emotions; we have also used econometric and machine learning techniques to explain and predict its helpfulness. We found that content and title polarity lead to OHRs being less helpful, whereby this negative relationship gets accentuated with higher sentiment content. On the other hand, while negative emotion with low arousal makes OHR helpful, high arousal makes it less helpful. It has also been noted that after controlling for polarity, sentiment, and emotions, longer reviews are less helpful. Higher quantitative rating, recency of OHR and a reviewer’s past expertise make a review more helpful. Additionally, machine-learning techniques have been found to predict ‘review’ helpfulness marginally better than econometric techniques. This study contributes to OHR literature in terms of its performance, and would also help decision makers in OHR management strategy.     

Understanding the dynamics of the quality of airline service attributes: Satisfiers and dissatisfiers

This research aims to determine the relationship between the quality of airline service attributes and overall satisfaction. Although a number of relevant studies have reported a linear relationship (or symmetric effect) between the two concepts, this work suggests that attribute quality exerts heterogeneous effects on satisfaction or dissatisfaction. A total of 157,035 consumer data from online reviews have been analyzed to achieve the research objective. In accordance with Herzberg, Mausner, and Snyderman’s (1959) two-factor theory, the findings of this research have determined that the quality of certain service attributes, such as cleanliness, food and beverages, and in-flight entertainment, affects the variations of positive ratings as a satisfier. Other airline service attributes, such as customer service and check-in and boarding, influence the deviations of negative ratings as a dissatisfier. Apart from airline attributes, the individual features and types of airline products have been estimated to improve the understanding of such relationships. In this regard, this study provides important implications to customer-centric marketing in an airline marketplace.     

Applying loss aversion to assess the effect of customers’ asymmetric responses to service quality on post-dining behavioral intentions: An empirical survey in the restaurant sector

Using the loss aversion concept, this paper attempts to investigate the relationship between service quality and customers’ post-dining behavioral intentions in the restaurant sector. Incorporating the DINESERV instrument, the results gained from a Chinese chain restaurant indicate that a decrease in service quality from the reference point (customer's expectation) will decrease the perceived service value and customer satisfaction, but that an increase in service quality may not have significant effects on these two behavioral constructs. Moreover, the behavior-related causal relationships underlying service quality suggest that perceived service value and attitudinal loyalty succeed in acting as mediating variables within the model.     

If memory serves: The effect of restaurant servers’ memorization and muddling of orders

The three experiments presented here examined the effectiveness of restaurant servers who memorize customers’ orders rather than writing orders down. In the experiments, participants viewed videos of simulated server-diner interactions and provided ratings of service quality and expected tip amount. Experiment 1 found no advantage to memorizing orders over writing them down. Experiment 2 found that memorized and correctly delivered entrees resulted in statistically significant increases in customers’ perceptions of service quality and in marginally higher tips. In addition, muddled (versus correct) orders resulted in lower ratings of service quality and dramatically lower anticipated tips. Experiment 3 found that memorizing and muddling complex orders had no effect on perceptions of service quality but led to significantly lower expected tips. The applied and theoretical implications of these results are discussed.     

Comparative study of deep learning models for analyzing online restaurant reviews in the era of the COVID-19 pandemic

Online reviews remain important during the COVID-19 pandemic as they help customers make safe dining decisions. To help restaurants better understand customers’ needs and sustain their business under current circumstance, this study extracts restaurant features that are cared for by customers in current circumstance. This study also introduces deep learning methods to examine customers’ opinions about restaurant features and to detect reviews with mismatched ratings. By analyzing 112,412 restaurant reviews posted during January-June 2020 on Yelp.com, four frequently mentioned restaurant features (e.g., service, food, place, and experience) along with their associated sentiment scores were identified. Findings also show that deep learning algorithms (i.e., Bidirectional LSTM and Simple Embedding + Average Pooling) outperform traditional machine learning algorithms in sentiment classification and review rating prediction. This study strengthens the extant literature by empirically analyzing restaurant reviews posted during the COVID-19 pandemic and discovering suitable deep learning algorithms for different text mining tasks.     

The relationship between price paid and hotel review ratings: Expectancy-disconfirmation or placebo effect?

Whilst there is extant research focusing on the link between hotel reviews and pricing there is scant attention paid to the impact of pricing on hotel review ratings. This paper presents a large scale study based on a novel dataset of more than 44,000 guest review ratings linked to the prices paid for rooms of an European hotel group. Through applying a panel regression analysis we reveal that expectancy-disconfirmation is generally stronger than the placebo effect and higher prices have a negative effect on review ratings, not only when assessing perceived value for money but also when evaluating perceived quality. We identify the trip and guest characteristics which impact on the price-review relationship. Findings provide hotel managers with key quantitative information for simultaneously calibrating quality and revenue targets. Substantial implications include an integrated approach for segmentation as a route to better manage pricing, revenue optimization and reputation.     

Image effect on customer-centric measures of performance

This study analyzes the effect of the difference between the pre-trip image of a destination and the post-trip image on, for the first time, two key elements of traveler behavior, which in turn are two customer-centric measures of destination performance: travel satisfaction and intention to revisit a destination. While the literature on the analysis of destination image has been prolific, the intricacies of the effects of changes in destination image on traveler behaviors remain unexplored, behaviors whose relevance is still greater when they show destination performance indicators. Based on the concepts of the zone of tolerance (derived from the service quality model) and loss aversion (from prospect theory), we explain the differential asymmetric effects of variation in destination image on intention to revisit and satisfaction, based on a sample of 12,024 individuals. Critical implications for destination marketing organizations are provided.     

Unravelling the effects of cultural differences in the online appraisal of hospitality and tourism services

International travelling has increased the likelihood of service interactions between customers and providers of different nationalities, frequently speaking various language, and repeatedly experiencing issues with intercultural communication. By examining more than 700,000 online reviews written by hotel guests of 101 different nationalities, using 84 different languages in their reviews, this study unravels cultural differences and examines through a direct measurement approach the simultaneous influence of national and linguistic differences between service customers and providers on online review valence. After controlling for reviewers’ demographics, behavioral features, trip related factors and location of service provider, the study findings reveal that while the influence of national cultural distance on online ratings is country- and destination- dependent, the usage of a common language is positively associated with online review valence irrespective of the destination/country where the service provider is located. Theoretical and practical implications are discussed.     

The effects of restaurant servers’ perceptions of customers’ tipping behaviors on service discrimination

Scholars have noted that the institution of tipping may encourage restaurant servers to provide discriminate service. The prospect of receiving an excellent tip from a patron, for example, is thought to encourage servers to discriminately provide excellent service. In contrast, the prospect of receiving a poor tip from a patron is thought to encourage servers to extend service that is commensurately poor. The effects of service workers’ a priori assumptions about customers’ tipping behaviors on service discrimination have however not been adequately assessed to-date. This article addresses this gap in the literature by assessing how server sensitivity to demographic tipping differences affects their proclivities to discriminately provide either excellent or poor service in response to the prospect of receiving an excellent or poor tip, respectively. Using a multilevel modeling technique (HLM), findings show that server sensitivity to demographic tipping differences is predictive of servers’ propensities to discriminately allocate excellent service but not poor service. The implications for the management of restaurant operations along with directions for future research are discussed.     

Let's hook up fast! Hotel reviews and Wi-Fi flaws

Free Wi-Fi connection is a prevalent service in the modern hotel industry. The effects of Wi-Fi services on customers' satisfaction have been investigated in existing literature. However, the attributes that lead to customers' negative reviews on hotels and the effects of these attributes on hotel ratings remain unexplored. Therefore, this article attempts to fill this gap by using a sample of 4800 reviews and estimating a Heckit model. This methodology allows us to model customers' decisions to write a negative review and rate a hotel simultaneously. The effects of Wi-Fi flaws on hotels' overall ratings are estimated and discussed. Moreover, important managerial implications are consequently derived. Reference dependence and sample selection bias also remain critical when analyzing hotel ratings.     

The effectiveness of managing social media on hotel performance

This paper investigates how managing online reviews affects hotel performance. An international hotel chain provided the hotel performance data and the online review data. A leading social media firm for the hospitality industry collected the online review data, which the hotel company purchased. The results indicate that overall ratings are the most salient predictor of hotel performance, followed by response to negative comments. The better the overall ratings and the higher the response rate to negative comments, the higher the hotel performance. Therefore, online reviews in social media, specifically overall rating and response to negative comments, should be managed as a critical part of hotel marketing.     

Sentiment and guest satisfaction with peer-to-peer accommodation: When are online ratings more trustworthy?

This study aims to decode guest satisfaction with peer-to-peer accommodations by analyzing the relationship between guests’ sentiment and online ratings and examining how analytical thinking and authenticity influence this relationship. Based on reviews of 4602 Airbnb listings in San Francisco, we empirically find that positive (negative) sentiment is linked to a high (low) rating. We further show that this link is stronger when guests manifest a higher extent of analytical thinking and authenticity. Both Tobit and ordered logit models yield consistent estimation results, showing the robustness of our findings. Our study contributes to the tourism and hospitality literature by theoretically explaining the association between sentiment and ratings. In addition, this paper enriches our knowledge regarding the trustworthiness of Airbnb ratings.     

How risky are services? An empirical investigation on the antecedents and consequences of perceived risk for hotel service

Previous research does not systematically investigate the antecedents and consequences of perceived risk for services in emerging markets. The present research aims to fill this void in the literature and examines the determinants and consequences of consumer risk perceptions for an experience service, hotel service. The present research models the antecedents at both the firm (company reputation and perceived price) and individual consumer (risk aversion and face consciousness) levels, and the consequences comprise word-of-mouth communication and switching intention. Though perceived risk is a multidimensional construct, past research tends to operationalize risk narrowly as either performance or financial risk. The author overcomes this limitation by studying perceived risk at the component level, and examines psychological, social, performance and financial risks separately. The results of a survey on Chinese consumers who have purchased hotel service recently indicate that both firm-level and individual-level antecedents directly influence perceived risk. While psychological and social risks positively affect word-of-mouth, they do not have significant influence on switching intention. In addition, performance risk increases switching intention but decreases word of mouth. The author discussed the theoretical and managerial implications, and suggested future research directions.     

Joint effects of management responses and online reviews on hotel financial performance: A data-analytics approach

Hotels are increasingly shifting their online review strategy from passive listening to proactive engagement through management responses. This study investigates the joint effects of management responses and online reviews on hotel financial performance. Based on a large unique dataset of 22,483 management responses to 76,649 online consumer reviews on TripAdvisor over 26 quarters, matched with quarterly hotel financial performance, this study finds that providing timely and lengthy responses enhances future financial performance, whereas providing responses by hotel executives and responses that simply repeat topics in the online review lowers future financial performance. Moreover, review rating and review volume moderate the effects of management responses. When the average review ratings increase, more management responses of greater length should be provided. As review volume grows, the benefits of providing timely and lengthy responses diminish. The study findings generate new implications for managing responses to online reviews to increase hotel financial performance.     

Differentiated price loss aversion in destination choice: The effect of tourists’ cultural interest

This article looks into the differentiated effects of loss aversion depending on whether individuals show cultural interest when choosing a destination. Based on the fact that perceived value implies not only sacrifices but also the expectations of a certain level of quality and prospects of satisfaction, together with the idea the Prospect Theory applies to tourism prices, the article states the hypothesis that interest in culture when choosing a destination lowers people’s loss aversion. By incorporating the reference-dependent model into a Multinomial Logit Model with Random Parameters – which controls for heterogeneity – the empirical application shows that culture-interested tourists are less loss averse; i.e. the negative effect of finding a higher than expected price diminishes with cultural interest. The expectation of enjoyment of these attributes and the more conscious attitude toward maintenance/restoration activities of cultural sites are hypothesized to lead prices to be evaluated differently when selecting a destination.     

Identifying salient attributes of peer-to-peer accommodation experience

This study explores key content and themes from online reviews to explain major service attributes of peer-to-peer (P2P) accommodation sought by guests. The results from lexical analyses indicate that attributes frequently mentioned in guest reviews are associated with location (proximity to point of interest and characteristics of neighborhood), host (service and hospitality), and property (facilities and atmosphere). Reviews focusing on location and feeling welcome are consistently linked with higher rating scores, including accuracy, cleanliness, check-in, communication, value, and overall ratings. This confirms that P2P accommodation appeals to consumers who are driven by experiential and social motivations. Marketing implications are provided.     

Effect of consumer sentiment on hospitality expenditures and stock returns

Given the importance of consumers to the U.S. economy and especially to the hospitality industry, we explore how consumer sentiment (i.e. confidence in the economy) affects consumption expenditures and stock returns in the hospitality industry.We find that not only does consumer sentiment partly predict changes in future consumption expenditures, but changes in consumer sentiment are contemporaneously related to hospitality industry stock returns. More importantly, our results indicate that changes in consumer sentiment can partly predict changes in stock prices of hospitality firms, an indicator of firm performance. The predictive ability of consumer sentiment can thus be useful to managers in business forecasting, planning, and strategizing for profit maximization.     

Evaluating domestic bias on airline passengers’ ratings: The moderating effect of cultural value orientation

We explore differences in airline passengers’ online ratings toward domestic and foreign carriers. Using a dataset of more than 380,000 airline passenger reviews obtained from TripAdvisor, we show that on average passengers express higher satisfaction (as proxied by their overall rating) for airline service encounters with domestic carriers, exhibiting a form of domestic bias. Using Hofstede’s framework, we examine how cultural dimensions influence the strength of this bias and find support for the moderating impact (positive and negative) of passengers’ cultural dimensions on their provided ratings toward domestic airlines. The study has theoretical and practical implications for international marketing researchers and airline operational planners.