Hotel Reviews Research Articles

Did COVID-19 change preferences for hygiene-related service attributes as satisfiers and dissatisfiers? An analysis of textual content of online hotel reviews

This study is a preliminary attempt to explore the impacts of COVID-19 on the changing roles of satisfiers and dissatisfiers in hotel service attributes. We analyzed online reviews posted between August 1st, 2019, and July 31st, 2022, for New York City hotels. Our results confirm that as a result of COVID-19, hygiene-related services are more likely to be perceived as satisfiers and less likely as dissatisfiers. COVID-19 was found to have an immediate negative effect on the occurrence of hygiene-related words in the negative aspects of online reviews, but this impact diminishes during the later phase. COVID-19 was found to have a steady positive effect on the occurrence of hygiene-related words in the positive aspects of online reviews.

How Online Travel Reviews Sources Affect Travelers’ Behavioral Intentions? Analysis with Source Credibility Theory

ABSTRACT This study used Source Credibility Theory (SCT) to examine the effect of the source credibility factors (SCFs) of travelers’ electronic word of mouth (eWOM) and their adoption on tourists’ hotel booking and review sharing intention. This study used Structure Equation Modeling (SEM) and artificial neural network (ANN) approaches to validate the effect of SCFs on tourists’ behavioral intentions. The study highlighted that all three source credibility factors, such as perceived sender trust, website trust, and organizational reputation, affected functional aspects like eWOM credibility and adoption. The study finds the dual-mediating effect of eWOM credibility and adoption between source credibility factors and eWOM outcomes. This study makes a unique attempt to analyze the roles of various aspects of SCT on tourists’ eWOM behavior. This study contributes to online trust literature by examining the effect of different online credibility factors (surface credibility, presumed credibility, reputed credibility) on online tourist behavior.

Attention-based Sentence Extraction for Aspect-based Sentiment Analysis with Implicit Aspect Cases in Hotel Review Using Machine Learning Algorithm, Semantic Similarity, and BERT

Attention-based Sentence Extraction for Aspect-based Sentiment Analysis with Implicit Aspect Cases in Hotel Review Using Machine Learning Algorithm, Semantic Similarity, and BERT

Hotel Reviews and Ratings and their Impact of Hotel Booking Behavior of Travelers: An Empirical Study

Hotel Reviews and Ratings and their Impact of Hotel Booking Behavior of Travelers: An Empirical Study

Arabic Sentiment Analysis Based on Word Embeddings and Deep Learning

Social media networks have grown exponentially over the last two decades, providing the opportunity for users of the internet to communicate and exchange ideas on a variety of topics. The outcome is that opinion mining plays a crucial role in analyzing user opinions and applying these to guide choices, making it one of the most popular areas of research in the field of natural language processing. Despite the fact that several languages, including English, have been the subjects of several studies, not much has been conducted in the area of the Arabic language. The morphological complexities and various dialects of the language make semantic analysis particularly challenging. Moreover, the lack of accurate pre-processing tools and limited resources are constraining factors. This novel study was motivated by the accomplishments of deep learning algorithms and word embeddings in the field of English sentiment analysis. Extensive experiments were conducted based on supervised machine learning in which word embeddings were exploited to determine the sentiment of Arabic reviews. Three deep learning algorithms, convolutional neural networks (CNNs), long short-term memory (LSTM), and a hybrid CNN-LSTM, were introduced. The models used features learned by word embeddings such as Word2Vec and fastText rather than hand-crafted features. The models were tested using two benchmark Arabic datasets: Hotel Arabic Reviews Dataset (HARD) for hotel reviews and Large-Scale Arabic Book Reviews (LARB) for book reviews, with different setups. Comparative experiments utilized the three models with two-word embeddings and different setups of the datasets. The main novelty of this study is to explore the effectiveness of using various word embeddings and different setups of benchmark datasets relating to balance, imbalance, and binary and multi-classification aspects. Findings showed that the best results were obtained in most cases when applying the fastText word embedding using the HARD 2-imbalance dataset for all three proposed models: CNN, LSTM, and CNN-LSTM. Further, the proposed CNN model outperformed the LSTM and CNN-LSTM models for the benchmark HARD dataset by achieving 94.69%, 94.63%, and 94.54% accuracy with fastText, respectively. Although the worst results were obtained for the LABR 3-imbalance dataset using both Word2Vec and FastText, they still outperformed other researchers’ state-of-the-art outcomes applying the same dataset.

Global Expectations, Local Realities: All-Inclusive Hotel Reviews and Responses on TripAdvisor

Abstract In this article we examine online reviews and hotel responses of Spanish hotel chains in two overseas tourist destinations: the Caribbean and Mexico. Drawing on a dataset of 96 hotel reviews we examine the intercultural experience of travellers as mediated by direct or indirect prior knowledge of the tourist destination and subsequent knowledge that results from visiting the host country and interacting with the locals, primarily with resort staff. The analysis shows, on the one hand, the global stance taken by the travellers to construct their reviews where the creation of an “intercultural space” is typically resisted and challenged in favour of expected global standards. The hotels’ responses, on the other hand, are constructed from a local rather than a global perspective. Findings reveal the intercultural tension that arises when lived experience of the specific culture cannot be married with the expectancies of homogeneity created by an increasingly globalised experience of tourism. The article concludes with a discussion of the role of interculturality, as conceived of in pragmatics, in a contemporary era characterised by discontent with digital information systems. It includes a discussion of some of the challenges in deploying the contrastive pragmatics toolkit to capture the intercultural space reported here and the extent to which it allows us to portray interculturality in the present day.

Deciphering Predictors of Tourists’ Value and Intention amid COVID-19: The Interplay of Scarcity, Enjoyment, Visual Presentations, and Pandemic Threat

The study investigates the factors influencing tourists’ online booking intentions. This study employed structural equation modeling to evaluate the online booking intentions of tourists after the second wave of the COVID-19 outbreak in India, extending the application of reactance theory in tourism and hospitality services. Mediation and moderation analysis facilitated the unfurling of direct and indirect linkages among the constructs. The findings suggest that online hotel reviews, perceived scarcity, and perceived enjoyment aggrandize tourists’ perceived value quotients, escalating their online booking intentions. Besides, visual presentations improve the strength of the linkage, while perceived pandemic threat weakens the linkage between tourists’ perceived value and online booking intentions. The research demystifies critical facilitators of tourists’ perceived value and online booking intentions that may assist hotel owners in engaging potential tourists and maximizing their hotels’ bottom line. The hotel industry lacks research on perceived scarcity, visual presentations, and perceived pandemic threat. This research adds to the body of knowledge by combining the abovementioned factors through a coherent theoretical framework. It makes prospective tourists cautious about COVID-19’s virulence and the devastating consequences.

A semi supervised approach to Arabic aspect category detection using Bert and teacher-student model.

Aspect-based sentiment analysis tasks are well researched in English. However, we find such research lacking in the context of the Arabic language, especially with reference to aspect category detection. Most of this research is focusing on supervised machine learning methods that require the use of large, labeled datasets. Therefore, the aim of this research is to implement a semi-supervised self-training approach which utilizes a noisy student framework to enhance the capability of a deep learning model, AraBERT v02. The objective is to perform aspect category detection on both the SemEval 2016 hotel review dataset and the Hotel Arabic-Reviews Dataset (HARD) 2016. The four-step framework firstly entails developing a teacher model that is trained on the aspect categories of the SemEval 2016 labeled dataset. Secondly, it generates pseudo labels for the unlabeled HARD dataset based on the teacher model. Thirdly, it creates a noisy student model that is trained on the combined datasets (∼1 million sentences). The aim is to minimize the combined cross entropy loss. Fourthly, an ensembling of both teacher and student models is carried out to enhance the performance of AraBERT. Findings indicate that the ensembled teacher-student model demonstrates a 0.3% improvement in its micro F1 over the initial noisy student implementation, both in predicting the Aspect Categories in the combined datasets. However, it has achieved a 1% increase over the micro F1 of the teacher model. These results outperform both baselines and other deep learning models discussed in the related literature.

Deep learning-based application for multilevel sentiment analysis of Indonesian hotel reviews

PurposeIn this study, we present a web-based application that retrieves hotel review documents in Indonesian languages from an online travel agent (OTA) and analyses their sentiments from the coarse-grained document to the fine-grained aspect level. Design/Methodology/Approach: There are four main stages in this study: development of sentiment analysis model at the document level based on a convolutional neural network (CNN), development of sentiment analysis model at the aspect level based on an improved long short-term memory (LSTM), model deployment for multilevel sentiment analysis in a web-based application, and its performance evaluation. The developed application uses several sentiment visualizations types at coarse-grained and fine-grained levels, such as pie charts, line charts, and bar charts. FindingThe application's functionality was demonstrated in practice based on three datasets from three OTA websites, which were analyzed and evaluated based on several matrices, namely, the precision, recall, and F1-score. The results revealed that the performance for the F1-score was 0.95 ± 0.03, 0.87 ± 0.02, and 0.92 ± 0.07 for document-level sentiment analysis, aspect-level sentiment analysis, and aspect-polarity detection, respectively. OriginalityThe developed application (Sentilytics 1.0) can analyze sentiment at document and aspect levels. The two levels of sentiment analysis are based on two models generated by fine-tuning CNN and LSTM models using specific architectures and domain data (Indonesian hotel reviews).

Has COVID-19 Changed Consumers’ Satisfiers and Dissatisfiers? Evidence from Online Reviews of 5-Star Hotels in Shanghai and Beijing

ABSTRACT Many studies have analyzed the asymmetric relationship between hotel service quality attributes and satisfaction, and tried to find consumers’ satisfiers and dissatisfiers, aiming at enhancing satisfaction more efficiently. However, the impact of COVID-19 has led to changes in consumers’ expectations for hotel services, and the above findings might face invalidation. To date, we are still unknown whether consumers’ satisfiers/dissatisfiers changed. This study fills this research gap by mining online reviews of five-star hotels from Shanghai and Beijing before and during the pandemic. The results found that the asymmetric categories of Sleep quality and Internet/Wi-Fi attributes have changed. Specifically, Sleep quality and Internet/Wi-Fi became dissatisfiers from hybrids, indicating that hoteliers only need to maintain their normal performance, and do not invest too many resources because they bring no satisfaction; attributes like Room, decoration, etc. remain hybrids. Additionally, we performed opinion extraction for the dissatisfier attributes to further understand what causes consumer dissatisfaction. The results contribute to the literature by shedding light on the pandemic’s impacts on the asymmetric effects of service quality attributes. The cause analysis can help hoteliers develop specific measures to mitigate the adverse effects of COVID-19.

User Opinion Prediction for Arabic Hotel Reviews Using Lexicons and Artificial Intelligence Techniques

Opinion mining refers to the process that helps to identify and to classify users’ emotions and opinions from any source, such as an online review. Thus, opinion mining provides organizations with an insight into their reputation based on previous customers’ opinions regarding their services or products. Automating opinion mining in different languages is still an important topic of interest for scientists, including those using the Arabic language, especially since potential customers mostly do not rate their opinion explicitly. This study proposes an ensemble-based deep learning approach using fastText embeddings and the proposed Arabic emoji and emoticon opinion lexicon to predict user opinion. For testing purposes, the study uses the publicly available Arabic HARD dataset, which includes hotel reviews associated with ratings, starting from one to five. Then, by employing multiple Arabic resources, it experiments with different generated features from the HARD dataset by combining shallow learning with the proposed approach. To the best of our knowledge, this study is the first to create a lexicon that considers emojis and emoticons for its user opinion prediction. Therefore, it is mainly a helpful contribution to the literature related to opinion mining and emojis and emoticons lexicons. Compared to other studies found in the literature related to the five-star rating prediction using the HARD dataset, the accuracy of the prediction using the proposed approach reached an increase of 3.21% using the balanced HARD dataset and an increase of 2.17% using the unbalanced HARD dataset. The proposed work can support a new direction for automating the unrated Arabic opinions in social media, based on five rating levels, to provide potential stakeholders with a precise idea about a service or product quality, instead of spending much time reading other opinions to learn that information.

Tracking Brand-Associated Polarity-Bearing Topics in User Reviews

Abstract Monitoring online customer reviews is important for business organizations to measure customer satisfaction and better manage their reputations. In this paper, we propose a novel dynamic Brand-Topic Model (dBTM) which is able to automatically detect and track brand-associated sentiment scores and polarity-bearing topics from product reviews organized in temporally ordered time intervals. dBTM models the evolution of the latent brand polarity scores and the topic-word distributions over time by Gaussian state space models. It also incorporates a meta learning strategy to control the update of the topic-word distribution in each time interval in order to ensure smooth topic transitions and better brand score predictions. It has been evaluated on a dataset constructed from MakeupAlley reviews and a hotel review dataset. Experimental results show that dBTM outperforms a number of competitive baselines in brand ranking, achieving a good balance of topic coherence and uniqueness, and extracting well-separated polarity-bearing topics across time intervals.1

Explaining tourist revisit intention using natural language processing and classification techniques

Revisit intention is a key indicator of business performance, studied in many fields including hospitality. This work employs big data analytics to investigate revisit intention patterns from tourists’ electronic word of mouth (eWOM) using text classification, negation detection, and topic modelling. The method is applied on publicly available hotel reviews that are labelled automatically based on consumers’ intention to revisit a hotel or not. Topics discussed in revisit-annotated reviews are automatically extracted and used as features during the training of two Extreme Gradient Boosting models (XGBoost), one for each of two hotel categories (2/3 and 4/5 stars). The emerging patterns from the trained XGBoost models are identified using an explainable machine learning technique, namely SHAP (SHapley Additive exPlanations). Results show how topics discussed by tourists in reviews relate with revisit/non revisit intention. The proposed method can help hoteliers make more informed decisions on how to improve their services and thus increase customer revisit occurrences.

Hotels’ environmentally-framed eWOM. The moderating role of environmental culture

Consumers are increasingly concerned about sustainable development. This study investigates the impact of environmentally-framed reviews on review rating scores considering the moderation of the reviewer's country's environmental performance. We use ordered logistic and linear regression analysis on a dataset of 45k TripAdvisor reviews of green hotels posted by reviewers from 150 countries. The findings reveal that environmentally-framed reviews are associated with higher rating scores, and the reviewer's country's environmental performance positively moderates this impact. This indicates that the environmental ranking of the reviewer's country of origin influences environmentally-framed eWOM about green and non-green services.

Content analysis of hotel reviews as a quality management tool: Preliminary verification of the SERVQUAL scale

The purpose of this paper is to identify the main factors for the quality of hotel services and to verify the SERVQUAL measurement scale commonly used in the services sector. In order to achieve this goal, an innovative approach of quantitative and qualitative content analysis of reviews published by users of the reservation portals Hotels.com and Booking.com was used. The study was based on more than 167,000 opinions on 3,4,5-star hotels located in Warsaw. They were ‘scraped’ with an indexing robot. The research outlines a list of the most important topics raised in those comments which correspond to the factors of perceived service quality of hotels. Among these are location, room attributes, cleanliness, breakfast and staff. In addition, the most important criteria used by customers to describe each of the listed elements are also reported. The results made it possible to identify differences between the operationalization of the constructs indicated in the SERVQUAL scale and the descriptions of each factor in the spontaneous comments of internet users. Thus, the need for adjustment to the current operationalizations of the SERVQUAL model to better reflect the sentiments of consumers in the hotel industry, or even developing a completely new tool for measuring service quality, was demonstrated.

‘Apparent’ and actual hotel scores under Booking.com new reviewing system

In September 2019, Booking.com changed its reviewing system based on the simple average of six items on a 2.5–10 scale by an unrestricted valuation on a 1–10 scale. This change has resulted in the drop of observed average scores. However, it is unclear which part of the shrinkage is due to the scale adjustment and which to priorly neglected aspects that consumers consider when valuing their satisfaction with the hotel stay. Using a dataset of more than 429,000 individual reviews for hotels in Madrid, Barcelona, Rome, Milan and Lisbon before and after the change, this paper disentangles apparent from actual changes in scores produced by the new scoring system. Using linear regressions and Propensity Score Matching, we show that, once the scale effect is left out, the new system has led to an increase by around 0.1 points in the actual valuation. Our results are potentially explained by the existence of unpacking effects.

Sentiment analysis and research based on two‐channel parallel hybrid neural network model with attention mechanism

AbstractConcerning the problems that the traditional Convolutional Neural Network (CNN) ignores contextual semantic information, and the traditional Recurrent Neural Network (RNN) has information memory loss and vanishing gradient, this paper proposes a Bi‐directional Encoder Representations from Transformers (BERT)‐based dual‐channel parallel hybrid neural network model for text sentiment analysis. The BERT model is used to convert text into word vectors; the dual‐channel parallel hybrid neural network model constructed by CNN and Bi‐directional Long Short‐Term Memory (BiLSTM) extracts local and global semantic features of the text, which can obtain more comprehensive sentiment features; the attention mechanism enables some words to get more attention that highlights important words and improves the model's sentiment classification ability. Finally, the dual‐channel output features are fused for sentiment classification. The experimental results on the hotel review datasets show that the Accuracy of the proposed model in sentiment classification reaches 92.35% and the F1 score reaches 91.59%.

Sentiment Analysis Of Hotel Reviews On Tripadvisor With LSTM And ELECTRA

This study examines the importance of hotel review data analysis and the use of Natural Language Processing (NLP) technology in predicting hotel review sentiment. In this study, deep learning models such as Long Short-Term Memory (LSTM) and Efficiently Learning an Encoder that Classifies Token Replacements Accurately (ELECTRA) are used to predict hotel review sentiment in Indonesian. Hotel review data was obtained through a data scraping process with webscraper.io from the Tripadvisor website and a total of 977 hotel review data were obtained from Grand Mercure Maha Cipta Medan Angkasa. Before the sentiment prediction process is carried out, hotel review data must go through the text preprocessing stage to remove punctuation marks, capital letters, stopwords, and a lemmatizer process is carried out to facilitate further data processing. In addition, sentiments that were previously unbalanced need to be balanced through the undersampling process. The data that has been cleaned and balanced is then labeled as negative (0), neutral (1) and positive (2) sentiments. The test results show that the ELECTRA model produces better performance than the LSTM with an accuracy of 47% by ELECTRA and 30% by LSTM.

Identifying memorable hotel experiences: analysis of TripAdvisor reviews

Abstract This article aims to (1) identify guests’ memorable experiences based on reviews posted on TripAdvisor, (2) identify the differences in memorable experiences due to hotel location, evaluation on TripAdvisor and consumer sentiment. The study used quantitative methods: text mining, topic modelling, and sentiment analysis. All reviews (n = 34,992) for all Warsaw hotels included on TripAdvisor (N = 99) were analysed. Seven topics of memorable experiences were identified via Latent Dirichlet Allocation analysis: five were very positive and two very negative. The content analysis of those topics allowed us to extract six positive factors which include: (1) view from the floor, (2) hotel staff and service, (3) breakfast and restaurant, (4) location and atmosphere, (5) pool, lounge, gym and spa, (6) price (value for money), as well as two negative factors: (1) noise at night, (2) booking and check-in. In addition, it was found that memorable hotel experiences differ depending on the location of the hotel in the city.

Review content type and hotel review helpfulness: direct and moderating effects

Review content type and hotel review helpfulness: direct and moderating effects