Understanding service attributes of robot hotels: A sentiment analysis of customer online reviews

Robots and artificial intelligence are essential to the future of the hospitality industry, and they are receiving increasing interest from hotel managers and researchers. However, the adoption of robotic services in hotel operations is a challenging task owing to the current level of technology and lack of understanding on the relationship between various aspects of robotic services and customer satisfaction. Moreover, no prior study has examined the service attributes of robots in hotels. To fill these gaps, this study analyzes customers’ sentiments on major hotels employing robotic services expressed through online reviews. A list of robot quality and operational area attributes is first constructed, through which underperforming robot service areas are identified. Sentiments on robotic services have a positive correlation with hotel service satisfaction, which plays an important role in determining the overall satisfaction of customers. The analysis and findings are valuable to researchers and managers for future research and adoption of robotic services in hotels.     

Exploring destination's negative e-reputation using aspect based sentiment analysis approach: Case of Marrakech destination on TripAdvisor

Tourism is entering a phase of intellectual changes characterized by consumer power's dynamism through social media. The immense amount of internet knowledge has become the number one means of communication globally through emails and social networks. Any Internet user can freely express themselves and give their views and feelings on any subject, including companies. The current research aims to provide a new technique by combining topic modeling and lexicon-based algorithms to gain insights about Marrakech's e-reputation, enhancing the tourism experience in this city. This study explores about 39,216 TripAdvisor reviews from different locations and attractions in Marrakech, Morocco. This approach is mainly based on Latent Dirichlet Allocation (LDA), to extract hidden aspects and dimensions from the feedbacks of tourists who visited Marrakech, search for some latent patterns inside the reviews and conduct Lexicon-based sentiment analysis to pinpoint the weaknesses directly and develop the touristic experience in this city.     

Can Response Management Benefit Hotels? Evidence from Hong Kong Hotels

With the growing influence of online reviews, more hotels are adopting online response management, but whether this works and benefits a hotel has rarely been studied. In this research, we study the impact of response management on hotel online ratings using data retrieved from TripAdvisor with a focus on Hong Kong hotels. We find that (1) high class hotels are more likely to adopt response management; (2) there is no significant difference among different hotel classes in terms of response rate; and (3) targeted response management has a significant positive effect on hotel ratings. In addition, Asian customers tend to give lower ratings than Western customers. We outline specific implications for hotel managers and their online management and offer suggestions for future research based on the empirical findings.     

Shopping experiences: International tourists in Beijing's Silk Market

This study examines international tourists' experiences in Beijing's Silk Market, one of the China's most well-known tourist markets. Tourists' spontaneous reviews on TripAdvisor were analyzed through Leximancer, a computer-assisted qualitative data analysis software. The study confirms that markets can be major tourism attractions and can provide important experiences for international tourists. Most international tourists were impressed with their Silk Market trip. The dominant narratives of their experiences were the “price” of the items they “bought”, the “fun” of “bargaining”, and the “fake” quality of the products. Further analyses show that different satisfaction groups used somewhat different narratives to represent their shopping experiences and that male international tourists enjoyed the Silk Market experiences more than their female counterparts.     

Big data for big insights: Investigating language-specific drivers of hotel satisfaction with 412,784 user-generated reviews

This study leveraged the advantages of user-generated reviews with the aim of offering new insights into the determinants of hotel customer satisfaction by discriminating among customers by language group. From a collection of 412,784 user-generated reviews on TripAdvisor for 10,149 hotels from five Chinese cities, we found that foreign tourists, who speak diverse languages (English, German, French, Italian, Portuguese, Spanish, Japanese, and Russian), differ substantially in terms of their emphasis on the roles of various hotel attributes (“Rooms,” “Location,” “Cleanliness,” “Service,” and “Value”) in forming their overall satisfaction rating for hotels. Chinese tourists domestically exhibit distinct preferences for room-related hotel attributes when compared to foreign tourists. Major interaction effects are revealed between the attributes “Rooms” and “Service” and between “Value” and “Service”.     

A comparison of destinations’ impacts on hotel rates

The impact of destinations’ attributes on hotel rates in different locations has been insufficiently compared the existing literature. This study sought to apply the hedonic pricing method to measure and compare how room prices are affected by factors that are both external and inherent to hotel companies. After collecting nearly all the data regarding hotel features that consumers can use to make choices about accommodations on the TripAdvisor website, different models were developed for each city and season. The results suggest that hotels in Barcelona are more dependent on external conditions than hotels in Madrid are. In addition, hotels in both cities are more affected by external conditions during the high season. This paper discusses these and other results, as well as their implications.     

Collaborative projects (social media application): About Wikipedia,the free encyclopedia

Collaborative projects—defined herein as social media applications that enable the joint and simultaneous creation of knowledge-related content by many end-users—have only recently received interest among a larger group of academics. This is surprising since applications such as wikis, social bookmarking sites, online forums, and review sites are probably the most democratic form of social media and reflect well the idea of user-generated content. The purpose of this article is to provide insight regarding collaborative projects; the concept of wisdom of crowds, an essential condition for their functioning; and the motivation of readers and contributors. Specifically, we provide advice on how firms can leverage collaborative projects as an essential element of their online presence to communicate both externally with stakeholders and internally among employees. We also discuss how to address situations in which negative information posted on collaborative projects can become a threat and PR crisis for firms.     

Insights into Suspicious Online Ratings: Direct Evidence from TripAdvisor

Online ratings and online reputation management are becoming increasingly popular and important. With this increasing importance, attempts to manipulate online reviews through fake reviews have become more prevalent. Suspicious online reviews (ratings) exist on many e-commerce platforms, but these reviews have rarely been observed and reported as manipulation in academic studies using different test methods. In our research, we examine empirical evidence of suspicious online ratings based on 41,572 ratings on TripAdvisor. Applying quantitative analytics, we find three important results: (1) the gap between overall rating and individual ratings does exist and is significant, especially among the lower class hotels; (2) the proportion of suspicious ratings is about 20% at a standard of 0.5; and (3) reviewers who tend to post excellent ratings are less likely to generate big gaps when posting ratings. We offer specific managerial implications for hotel managers on online reputation management and selected suggestions for future research based on the empirical findings.     

Improving text summarization of online hotel reviews with review helpfulness and sentiment

The considerable volume of online reviews for today's hotels are is difficult for review readers to manually process. Automatic review summarizations are a promising direction for improving information processing of travelers. Studies have focused on extracting relevant text features or performing sentiment analysis to compile review summaries. However, numerous reviews contain nonspecific or nonsentimental content, hindering the ability of sentiment-based techniques' to accurately summarize useful information from hotel reviews. This paper proposes a systematic approach that first constructs classifiers to identify helpful reviews and then classifies the sentences in the helpful reviews into six hotel features. Finally, the sentiment polarities of sentences are analyzed to generate the review summaries. Experiment results indicated that the performance of the proposed approach was superior to other methods.     

Experiencing the real village – a netnographic examination of perceived authenticity in rural tourism consumption

There is an upsurge of research interest regarding authenticity in contemporary tourism consumption as modern tourists have been found to prefer involve in real backstage experiences to participating in pseudo-events and mass congregations. This paper presents a netnographic analysis of tourists’ reviews on village destinations and explores how authenticity is experienced by tourists in a village setting and the indicators pertaining to it. Trip Advisor reviews of three Indian villages were downloaded and analysed. Findings reveal that tourists consider authenticity as a critical factor in rural village experience. The indicators of rural authentic experience and their implications are also highlighted.