Big Data and Sustainability in the Tourism Industry

This Special Issue (SI) of Sustainability titled “Big Data and Sustainability in the Tourism Industry” contains 11 papers.

Keeping in mind that sustainable tourism has become a topic of heated debate over the past few years, the tourism sector must adopt new competitive strategies and enhance organizational dynamism by incorporating big data analytics and business models into their operations. A vital goal of this SI is to improve our understanding of how big data analyses can create social and environmental values, as well as economic and financial sustainability in line with the principles of the Sustainable Development Goals (SDGs). Therefore, this SI features original and relevant conceptual and empirical papers on how big data analysis provides tourism actors, organizations, territories, and ecosystems with new opportunities for creating economic, social, and environmental values. We now provide a brief synopsis of each of the eleven papers accepted for this SI and then offer a conclusion of their contributions.

Hwang et al. (Contribution 1: “Robotic Restaurant Marketing Strategies in the Era of the Fourth Industrial Revolution: Focusing on Perceived Innovativeness”) investigated robotic technology’s role in the restaurant industry. With the proposed hypotheses and a sample of 418 restaurant customers, their empirical findings include the effect of perceived innovation on attitude. This study confirmed and expanded on the critical role played by perceived innovativeness in the innovation process. Their study found that perceived innovation helps improve attitudes towards robotic restaurants. Moreover, their results indicate that consumers’ perceived risk plays a moderating role (1) between desire and use intentions, and (2) between desire and willingness to pay. Thus, the authors extended the existing literature by finding the moderating role of perceived risk in the context of a robotic restaurant for the first time.

Shadiyar et al. (Contribution 2: “Extracting Key Drivers of Air Passenger’s Experience and Satisfaction through Online Review Analysis”) assessed online customer reviews between Korean airlines and Commonwealth Independent State (CIS) airlines. After their comparison, they pointed out that five out of six clusters are significantly different. In detail, there was a significant difference between Korean airlines and CIS airlines in seat comfort, staff, food and beverages, entertainment, and value for money. Another notable result was related to Korean airlines’ ratings and recommendations compared with CIS airlines. Nevertheless, the difference in the ground service cluster was not significant.

As South Korea has experienced fluctuating levels of tourist arrivals over time due to diverse circumstances and has complex relationships with tourism source countries, Choi and Kim (Contribution 3: “Co-Movement between Tourist Arrivals of Inbound Tourism Markets in South Korea: Applying the Dynamic Copula Method Using Secondary Time Series Data”) investigated if there are non-linear dependence structures between tourist flows into South Korea from five major source countries. Additionally, their study identified the structural characteristics of extreme tail dependence, which are prevalent in unpredictable events, in addition to identifying how the changes in co-movements vary over time via dynamic copula-GARCH tests (generalized autoregressive conditional heteroskedasticity). The three main findings based on their result were (1) the most prominent market pair being China and Taiwan; (2) the extreme tail dependencies in tourist flow movements to Korea existing across the source countries but, interestingly, China and Taiwan having no asymmetric extreme tail dependence even though they have the highest static dependency; and (3) the dynamic dependence structure being able to be used to identify co-movements for specific events, which indicates that Chinese and Taiwanese tourists complement each other.

Jung and others (Contribution 4: “A Study on Dining-Out Trends Using Big Data: Focusing on Changes since COVID-19”) compared the emotions and needs regarding dining-out experiences before and after the outbreak of the COVID-19 pandemic. Their first findings shown that the number of restaurant visits decreased significantly. Then they explored that before the COVID-19 pandemic, “dining-out”, “family”, “famous restaurant”, “recommend”, “dinner”, “delicious menu”, and “restaurants” were words that frequently appeared in the results. After the COVID-19 pandemic started, “taste”, “corona”, and “weekend” were the new words that frequently appeared. Moreover, consistent with the previous study, in which some scholars pointed out that new eating habits centered on food delivery or digital consumers emerged, this study suggested that changing the perception of dining-out may be due to negative emotions.

Cui et al. (Contribution 5: “The Economic Resilience Cycle Evolution and Spatial-Temporal Difference of Tourism Industry in Guangdong-Hong Kong-Macao Greater Bay Area from 2000 to 2019”) constructed a counterfactual function and investigated the evolution of the tourism industry’s spatial–temporal differences in the Guangdong–Hong Kong–Macao Greater Bay Area (GBA) over the past twenty years. In virtue of the perspective of industrial economic resistance and resilience, this study extended resilience theory into the tourism industry economy. It explained how tourism industry resilience differs from other industries in the metropolitan area system of GBA urban agglomeration.

The popularity of YouTube as a tourism information source is growing. Several factors have been identified as may be being able to predict view on YouTube about Incheon’s Chinatown in South Korea. Yoo et al. (Contribution 6: “Predictors of Viewing YouTube Videos on Incheon Chinatown Tourism in South Korea: Engagement and Network Structure Factors”) explored the network structures of videos about Incheon’s Chinatown in South Korea and examined their possible predictive factors. In their study, user engagement and video network structure were considered as determinants of the popularity of tourism videos on YouTube.

Zhang and Kim (Contribution 7: “Customer Experience and Satisfaction of Disneyland Hotel through Big Data Analysis of Online Customer Reviews”) targeted world-class theme hotels and explored and demonstrated how semantic network analysis, one of the most important areas of big data analytics, can be used to understand texts in the context of theme hotels in order to evaluate and analyze their customer experience through online reviews as well as to demonstrate to what extent their results can be used to evaluate and analyze customer experience.

Wei et al. (Contribution 8: “Estimating the Spatial Heterogeneity and Seasonal Differences of the Contribution of Tourism Industry Activities to Night Light Index by POI”) investigated the seasonal changes in night satellite image brightness and deeply considered their correlation and spatial heterogeneity with different tourism industry activities. It is in this study that a new method and perspective were introduced to the field of tourism research. In particular, this study aimed to analyze and research whether mathematical and spatial models should be based on the relationship between the seasons’ changes using point of interest (POI). Furthermore, it revealed the spatial differences in tourism activities along geographical lines, which can be used to determine the seasonality of tourism activities in the whole region as well as to investigate or reveal possible seasonal patterns. Data from different sources can be combined in the future to study the spatial distributions of tourism activities and their contribution to night light radiation. They provided guidance and suggestions for relevant departments on how to formulate night protection measures for tourism and to promote sustainable tourism development by evaluating the degree and spatial feature of carbon energy consumption and light pollution generated by various tourism activities.

In Kim and Kim’s (Contribution 9: “The Impact of Hotel Customer Experience on Customer Satisfaction through Online Reviews”) study, based on an analysis of online hotel reviews, they identified the key attributes affecting customer satisfaction. Moreover, they examined how significant the impact those attributes were on the perception of satisfaction of consumers. Four clusters—destination, physical environment, service, and trip purpose—were determined to be related to the various facilities, location, service, and food and beverage that significantly contribute to enhancing hotel customer experience.

Sann et al. (Contribution 10: “Extracting Key Drivers of Air Passenger’s Experience and Satisfaction through Online Review Analysis”) aimed to enrich the published literature on hospitality and tourism by applying big data analytics and data mining algorithms to predict travelers’ online complaint attributions to significantly different hotel classes. The initial basis for guests’ complaints, as identified from this study, originated from 10 complaint variables and 52 item complaints through manual qualitative content analysis.

Choi et al. (Contribution 11: “How to Enhance Smart Work Effectiveness as a Sustainable HRM Practice in the Tourism Industry”) tried to answer whether utilizing smart work can actualize employee’s well-being and quality life. Targeting sustainability human resource management (HRM), they explored employees’ subjective opinions regarding smart work programs and how they can be enhanced. Furthermore, the results set managerial implications for improving smart work practices in future studies for sustainable HRM practices, which contributes to the achievement of SDGs. According to this effect, five types of smart work effectiveness have come to light: (1) self-development and energy saving, (2) quality of life, (3) job satisfaction, (4) work engagement, and (5) work–life balance.

Some broad conclusions can be drawn based on the papers in and the context of this SI.

The first conclusion of this SI is the influence of big data on the creation of social value in tourism. This philosophy is based on creating employee value, which includes fostering good working conditions, improving employee capacity, improving work–life balance and happiness, and fostering a harmony work environment. For instance, the paper by Choi et al. discussed sustainable HRM. The topic of their work revolved around how smart work implementation can be enhanced by examining how employees’ subjectivity can be used. With their finding of five categories of smart work effectiveness—self-development and energy saving, quality of life, job satisfaction, work engagement, and work–life balance—this study contributed to achieving SDGs by establishing proper managerial implications.

Big data analytics for sustainable tourism is the second concern of this SI. Tourism and the hotel industry, in particular, rely heavily on online reviews for decision-making. In another word, consumers deem online reviews to be more useful than the information provided by other online information sources since they consider the content of the reviews to be more compelling. Online communication platforms, the explosion of the bidirectional exchange of information on products and services, and the growing use of social media platforms have brought about many opportunities as well as some challenges with the rapid growth of online reviews, notifications, opinions, and recommendations in the tourism industry. Shadiyar et al. explored the sustainable tourism regarding airline companies. Zhang and Kim focused on the same topic regarding Disneyland hotels.

Moreover, research on big data social innovation is another focus that contributes to sustainable tourism and hospitality development. Social media as a source of travel-related information attracts consumers’ attention. On the basis of a social network analysis, Yoo et al. examined the features of network structures, the types of relationships within networks, the positions of nodes within networks, and the patterns of communication between nodes.

Sustainable economic growth of the tourism ecosystem is the fourth topic covered in this SI. As represented by Choi et al., several factors have contributed to significant fluctuations in tourist arrivals to destinations, including a variety of circumstances and complex relations among source countries for inbound tourism. Cui et al. divided and measured the tourism industry’s economic resilience cycle in the Guangdong–Hong Kong–Macao Greater Bay Area (GBA) by constructing a counterfactual function and by exploring the evolution of its spatial–temporal difference characteristics in the past 20 years and contributes three recession–recovery cycles. Thanks to these two meaningful studies, researchers have considered the gap regarding how to measure the interdependence of tourist arrivals from major source markets and what that means for the sustainability of the destination’s tourism industry.

Fifth, climate change and tourism in the big data environment is another focus. Wei et al.’s paper presented a revolutionary method for tourism research as well as uncovered geographic differences in the spatial distribution of tourism, which is of great interest when studying the spatial distribution and seasonality of tourism at the county level. As well as providing a reference and suggestions for relevant departments to formulate tourism night protection measures, their spatial evaluation of the contribution of tourism and luminous radiation also plays a vital role in determining the spatial coverage of the contribution.

Furthermore, scholars are unquestionably concerned about the importance of sustainable customer behavior and big data tools in tourism as a topic of interest. However, customer complaints are also important to consider. Based on online reviews, Kim and Kim assessed the hotel customer experience and investigated their association with customer satisfaction. Sann et al. predicted online complaining behavior (OCB) in the hospitality industry.

Besides the main themes in this SI, another significant contribution is the methodological approaches employed in analyzing technical and statistical data in the tourism and hospitality field. Sann et al. conducted their research based on machine learning algorithms. Their analysis used DT algorithms. Furthermore, they employed different model types to predict behavior, such as the C&RT, C5.0, and GUEST models. Wei et al.’s study utilized POI data analyzed by ordinary least squares (OLS) and geographically weighted regression (GWR). Choi et al. used the Q-methodology to collect employees’ detailed ideas about smart work that they have experienced. Yoo et al. from NodeXL collected video clips. Kim and his colleagues who work at Wellness & Tourism Big Data Research Institute (Kyungsung University, Republic of Korea) created a reliable research methodology and conducted a series of research based on SCTM (Smart Crawling & Text Mining, developed by the Wellness and Tourism Big Data Research Institute at Kyungsung University). With the power of science and technology and information platforms, the utilization and analysis of big data have made apparent contributions to academia.

It is evident from the papers included in this SI that timely research and theorizations have been conducted on the sustainability of the tourism and hospitality fields, which may aid in the formulation and construction of targeted strategies and tactics for big data utilization in the tourism and hospitality industry. While big data research is tremendously valuable for achieving evolutionary breakthroughs, it also faces severe challenges in various aspects, such as data capture, data analysis, data reliability, data privacy, etc. [1]. To address the above challenges, advanced artificial intelligence techniques will need to be applied to data collection and analysis to provide more accurate and detailed insights from representative big data samples to address the above challenges and to generate more precise and accurate insights from more extensive samples of big data. In addition, strengthening the collaboration between academia and industry can be a viable method to address the challenges of big data security and privacy.

For future research, we still need to understand the systemic nature of big data usage and its associated sustainability. Future directions of research include the re-emergence of the post-epidemic era, big data sustainable tourism, changes in the policies and regulations of the hospitality and restaurant industry, a people-oriented tourism environment, and high-tech co-creation. As a continuation of this SI and to address the issues raised above, another SI has launched in the section Psychology of Sustainability and Sustainable Development of the journal Sustainability, entitled as “Advances in Sustainable Psychology and Behavior: Managing and Developing People within the External and Organizational Environment”. The overall purpose of this new SI is to focus on people’s perceptions and behaviors the external and organizational contexts to better understand and manage people at work. A number of enrichment topics related to behavioral and psychological sustainability that rely on big data analytics are also anticipated.

Finally, we end this editorial with a proverb: “The good seaman is known in bad weather”; through the efforts of scholars and managers, the wide use of big data and technologies in the tourism industry will serve as a steering wheel, navigating the tourism industry to revitalize and achieve sustainable development amidst the cold winter of the COVID-19 pandemic.

List of Contributions

• Hwang, J.; Lee, K.; Kim, D.; Kim, I. Robotic Restaurant Marketing Strategies in the Era of the Fourth Industrial Revolution: Focusing on Perceived Innovativeness. Sustainability 2020, 12(21), 9165. https://doi.org/10.3390/su12219165.
• Shadiyar, A.; Ban, H.; Kim, H. Extracting Key Drivers of Air Passenger’s Experience and Satisfaction through Online Review Analysis. Sustainability 2020, 12(21), 9188. https://doi.org/10.3390/su12219188.
• Choi, K.; Kim, I. Co-Movement between Tourist Arrivals of Inbound Tourism Markets in South Korea: Applying the Dynamic Copula Method Using Secondary Time Series Data. Sustainability 2021, 13(3), 1283. https://doi.org/10.3390/su13031283.
• Jung, H.; Yoon, H.; Song, M. A Study on Dining-Out Trends Using Big Data: Focusing on Changes since COVID-19. Sustainability 2021, 13(20), 11480. https://doi.org/10.3390/su13031283.
• Cui, W.; Chen, J.; Xue, T.; Shen, H. The Economic Resilience Cycle Evolution and Spatial-Temporal Difference of Tourism Industry in Guangdong-Hong Kong-Macao Greater Bay Area from 2000 to 2019. Sustainability 2021, 13(21), 12092. https://doi.org/10.3390/su132112092.
• Yoo, W.; Kim, T.; Lee, S. Predictors of Viewing YouTube Videos on Incheon Chinatown Tourism in South Korea: Engagement and Network Structure Factors. Sustainability 2021, 13(22), 12534. https://doi.org/10.3390/su132212534.
• Zhang, X.; Kim, H. Customer Experience and Satisfaction of Disneyland Hotel through Big Data Analysis of Online Customer Reviews. Sustainability 2021, 13(22), 12699. https://doi.org/10.3390/su132212699.
• Wei, J.; Zhong, Y.; Fan, J. Estimating the Spatial Heterogeneity and Seasonal Differences of the Contribution of Tourism Industry Activities to Night Light Index by POI. Sustainability 2021, 13(22), 12699. https://doi.org/10.3390/su132212699.
• Kim, Y.; Kim, H. The Impact of Hotel Customer Experience on Customer Satisfaction through Online Reviews. Sustainability 2022, 14(2), 848. https://doi.org/10.3390/su14020848.
• Sann, R.; Lai, P.; Liaw, S.; Chen, C. Predicting Online Complaining Behavior in the Hospitality Industry: Application of Big Data Analytics to Online Reviews. Sustainability 2022, 14(3), 1800. https://doi.org/10.3390/su14031800.
• Choi, H.; Lee, J.; Choi, Y.; Juan, Y.; Lee, C. How to Enhance Smart Work Effectiveness as a Sustainable HRM Practice in the Tourism Industry. Sustainability 2022, 14(4), 2218. https://doi.org/10.3390/su14042218.

And all authors in this SI have contributed to the writing of the present editorial after having contributed to the research topic.