Intelligent exchange of sustainable tourist habits among the EU member states

Leal, Fátima; Pinho, Micaela Moreira Article Intelligent exchange of sustainable tourist habits among the EU member states Administrative Sciences Provided in Cooperation with: MDPI – Multidisciplinary Digital Publishing Institute, Basel Suggested Citation: Leal, Fátima; Pinho, Micaela Moreira (2024) : Intelligent exchange of sustainable tourist habits among the EU member states, Administrative Sciences, ISSN 2076-3387, MDPI, Basel, Vol. 14, Iss. 6, pp. 1-17, https://doi.org/10.3390/admsci14060128 This Version is available at: https://hdl.handle.net/10419/320944 Standard-Nutzungsbedingungen: Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden. Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen. Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. Terms of use: Documents in EconStor may be saved and copied for your personal and scholarly purposes. You are not to copy documents for public or commercial purposes, to exhibit the documents publicly, to make them publicly available on the internet, or to distribute or otherwise use the documents in public. If the documents have been made available under an Open Content Licence (especially Creative Commons Licences), you may exercise further usage rights as specified in the indicated licence. https://creativecommons.org/licenses/by/4.0/ Citation: Leal, Fátima, and Micaela Pinho. 2024. Intelligent Exchange of Sustainable Tourist Habits among the EU Member States. Administrative Sciences 14: 128. https://doi.org/ 10.3390/admsci14060128 Received: 26 April 2024 Revised: 3 June 2024 Accepted: 14 June 2024 Published: 19 June 2024 Copyright: © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/). administrative sciences Article Intelligent Exchange of Sustainable Tourist Habits among the EU Member States Fátima Leal 1,*,† and Micaela Pinho 1,2,3,† 1Research on Economics, Management and Information Technologies, REMIT, Portucalense University, 4200-072 Porto, Portugal; [email protected] 2Instituto Jurídico Portucalense, IJP, Portucalense University, 4200-072 Porto, Portugal 3Research Unit in Governance, Competitiveness and Public Policy, GOVCOPP, Aveiro University, 3810-193 Aveiro, Portugal *Correspondence: [email protected] †These authors contributed equally to this work. Abstract: Despite much research being conducted within the scope of sustainable tourism, more progress has yet to be made in defining how close or far different countries are from achieving this goal. Consequently, this paper aims to evaluate and compare the commitment of citizens, as tourists, from the 27 member states of the European Union to sustainable tourism. A map of sustainability was developed through the use of machine learning algorithms. A cluster analysis was performed, followed by a sustainable rating. The main findings indicate the existence of three country segments among the European Union member states according to the involvement of its citizens as tourists with sustainable practices: highly committed, moderately committed, and uncommitted. Based on these segments, we proposed a recommendation system that suggests the top-five countries where tourists could exchange sustainable tourism habits based on the idea of contagion or imitation behaviours among individuals across an extensive set of everyday decisions. The results reveal significant variations in sustainable tourism practices across member states, highlighting both challenges and opportunities for harmonisation. By implementing this recommendation system, we facilitate the adoption of sustainable habits among tourists and stakeholders, driving a more unified approach to sustainability in the multiple tourism destinations. This study shows no convergence between the 27 European Union member states regarding sustainable tourism. Therefore, political policies are necessary so that all citizens converge on sustainable tourist habits and the European Union contributes, as a whole, to sustainable tourism. Keywords: sustainable tourism; clustering; machine learning; tourists’ sustainable behaviours; sustainability information availability; recommendation systems 1. Introduction The planet is on fire and the world is in ‘great peril’, as the United Nations SecretaryGeneral said in 2022. He recently encouraged the political leaders gathered for the Conference of Parties (COP) 28 (taking place while this article is being written) to get us out of ‘deep’ troubles. The economic progress that we benefit from was achieved without considering the Earth’s natural limits. Humanity has made selfish decisions in pursuit of its maximum well-being, ignoring the costs they sow along the way, jeopardising the well-being of future generations (their children and grandchildren). Recognising that society will collapse when these limits are exceeded has been one of the first movers toward sustainability. There has been a widespread call for a sustainable form of development. Sustainable development seeks to rediscover the balance between the economy, society, and the environment. Sustainable development was first defined in the Brundtland Report released in 1987 by the World Commission on Environment and Development, as a level of development that meets the needs of the present without compromising the ability of Adm. Sci. 2024,14, 128. https://doi.org/10.3390/admsci14060128 https://www.mdpi.com/journal/admsci Adm. Sci. 2024,14, 128 2 of 17 future generations to meet their own needs Jarvie (2016). To signal their involvement and commitment to this cause, the United Nations developed the 2030 Agenda for Sustainable Development, comprising 17 sustainable development goals by 2030 United Nations (2015) by the 193 signatory countries. The tourism sector plays a vital role in this context. Tourism is a highly significant economic sector globally and locally. This service sector has grown exponentially in recent years (except the pandemic years), becoming one of the world’s largest industries. The positive economic impacts of tourism cannot be overstated. This sector generates revenues, creates jobs, and develops local communities while boosting other sectors such as transportation, hospitality, and retail. The tourism and travel industries represented 7.6% of the worldwide gross domestic product in 2022 Eurostat (2023), which will undoubtedly rise since the sector is still recovering from the COVID-19 pandemic. However, tourism benefits the state and simultaneously involves costs that translate into high flows of natural resources, excessive energy and water consumption, and increasing adverse environmental effects, including climatic change. According to the United Nations World Tourism Organisation (UNWTO) Organization and Forum (2019), tourism is estimated to contribute to 5.3% of worldwide carbon emissions in 2030. The impact of tourism on the environment began to be recognised in the late 1980s. Nash and Butlers (1990) created the concept of sustainable tourism to reduce the adverse effects of tourism activities. This topic is of the utmost importance for two main reasons. First, the tourism sector finds itself at a crossroads, as the continuity of the tourism industry depends on the health of the environment (e.g., healthy marine ecosystems are determinants for coastal and maritime tourism, while rich biodiversity and natural heritage are attractions in destinations) while simultaneously being a significant contributor to its destruction. Second, the tourism sector has the potential to contribute to the 17 Sustainable Development Goals (SDGs) (e.g., the tourism sector helps to eradicate poverty by creating jobs in local communities—SDG1—while the taxes it generates can be reinvested in the provision of health services, resulting in better health for all—SDG3). Sustainable tourism aims to guarantee a balance between protecting the environment, maintaining cultural integrity and social justice (Liu et al. 2013), promoting economic benefits to meet the needs of the host population for better standards of living (Park and Yoon 2009), and encouraging and cultivating tourism in lesser-known and less-frequented destinations. In this debate on sustainable tourism, circular tourism is gaining prominence, and, based on the theory of the circular economy, its numerous advantages for achieving more sustainable tourism have been put forward Axhami et al. (2023); Florido et al. (2019). Tourists’ pro-environmental behaviours are one of the main ways to achieve tourism sustainability, namely, through following certain practices such as reducing waste and water usage, choosing more ecological modes of transport, opting for local products, choosing less visited destinations, taking holidays outside the high season, and contributing to carbon-offsetting activities (Li and Wu 2020;Pronello and Gaborieau 2018;Wu et al. 2021). Sustainable tourism has become an increasing field of research (de Bruyn et al. 2023; Streimikiene et al. 2021;Yang et al. 2023), although this proliferation of the literature presents weaknesses (Liu et al. 2013). One of the most important limitations is considering the sustainability of destinations exclusively through a supply perspective. There is a need to rethink human–environment relations since tourists, through their behaviours/attitudes, play a crucial role in achieving sustainable tourism. Therefore, the focus should shift from the sustainable tourism supply side toward the demand side. Reaching a new tourism model with a central value in sustainability depends on the importance that tourists give to sustainability and how they are committed to contributing to it. In this regard, research has shown that a possible way to integrate sustainability into the planning of tourism destinations is to attract tourists who are intrinsically interested in protecting the destination they visit and, consequently, behave responsibly (Dolnicar 2006;Kastenholz et al. 2018). Therefore, to achieve sustainable tourism, it is necessary to determine the tourists’ heterogeneity to define segments based on the behaviours and attitudes associated with the sustainability philosophy to be analysed. The segmentation of the tourism market Adm. Sci. 2024,14, 128 3 of 17 and the definition of the size and relevance of each segment ensure the formulation of policies that are the most appropriate and tailored to the markets’ needs. Furthermore, data and information are paramount to achieving sustainable tourism, as this process is interactive. On the supply side, there is constant monitoring of impacts to, when necessary, introduce preventive and/or corrective measures O’Mahony et al. (2009). On the demand side, information concerning tourism destination sustainability may influence tourist travel planning Streimikiene et al. (2021) and make them more compelling with sustainable tourism Tang et al. (2022). Thus, information is crucial for implementing and monitoring sustainable tourism. Even so, a recent study reveals that, although the actors are more involved in monitoring tourism, their importance to environmental and social monitoring is lower than that given to economic monitoring Dias et al. (2023). Although there are a few segmentation studies on sustainable tourism (described in the next section), this domain lacks research to segment travellers considering both (i) the availability of tourists to change tourism habits and (ii) the relevance of accessing trustworthy sustainable information for travel planning. Additionally, no research has been conducted to explore the sustainable behaviour of European Union tourists. The present study aims to overcome these limitations and shed light on how to build an integrative framework of the state of sustainable tourism in the European Union (EU) to help formulate policies that lead all member states to achieve the same goal: to reach sustainable tourism in the EU as quickly as possible and thus become closer to reaching sustainable development as featured in the 2030 Agenda for Sustainable Development. The present paper intends to contribute to sustainable tourism development by providing information that contributes to the informed participation of all relevant stakeholders, namely, tourists, regulators, host community members, service providers, marketeers, and strong political leadership, to ensure wide participation and consensus building. Therefore, the current research aims to explore, through machine learning (ML), tourist segmentation by the 27 EU member states based on their sustainable travel habits and the availability of trustworthy sustainable information in tourism destinations. This study builds on secondary data from the Flash Eurobarometer 499—’Attitudes of Europeans towards Tourism’ (GESIS 2022), concerning 25,711 citizens from the 27 European Member States. The study takes place in two phases. First, a clustering analysis is conducted to group the data (countries) based on similarities in tourism sustainability (Rokach and Maimon 2005). Afterwards, to confirm the cluster analysis results, a sustainability rating by country is calculated. This aims to attribute a certain degree of sustainability to each European country based on tourist habits. In the second phase, an analysis per respondent is carried out. Here, the profile of each respondent is analysed and compared with the previous results to allocate each respondent to the previously defined clusters of countries. The allocation decisions or recommendations are processed by employing content-based filtering, which calculates the similarity between countries and the corresponding respondents. The intention is to create a ‘behavioural contagion effect’ based on the hypothesis defended in the literature that individuals mimic each other in everyday life, which may have significant environmental consequences (Zorell 2020). The main results suggest the existence of three countries’ segments according to the involvement of its citizens, as tourists, with sustainable practices: (i) highly committed (sustainable level 3); (ii) moderately committed (sustainable level 2); and (iii) uncommitted (sustainable level 1). Considering these three segments, for each respondent, five countries were recommended where the behaviour contagion effect can be increased regarding sustainability. This study is relevant to the sustainable tourism literature since it is the first to segment the 27 EU member states’ tourism paths through a combination of quantitative methods. The remainder of the paper is structured as follows. Section 2addresses the literature related to segmentation analysis in tourism sustainability. Section 3describes the proposed method. Section 4discusses the experimental results. Section 5discusses the results Adm. Sci. 2024,14, 128 4 of 17 comparing with the literature. Section 6presents the concluding remarks. Finally, Section 7 details the implication of this work in the tourism domain. 2. Related Work As global tourism expands, the imperative for sustainable practices within the industry becomes increasingly critical. Sustainable tourism aims to minimise environmental impacts, support local economies, and preserve cultural heritage, ensuring that tourism development meets the needs of present generations without compromising the ability of future generations to meet their own needs. The literature on sustainable tourism is vast and multifaceted, encompassing various strategies and approaches designed to promote sustainability across different segments of the tourism market and the role of technology in multiple SDGs. This paper addresses an intelligent exchange of sustainable tourism habits by employing a segmentation analysis and a recommendation system. Sustainable tourism and segmentation explore the diverse market segments within the tourism industry and how tailored sustainable practices can effectively address the unique needs and behaviours of different tourist groups. By understanding the distinct characteristics and motivations of various segments, stakeholders can develop targeted strategies that enhance the adoption of sustainable practices. Recommendation approaches for sustainable tourism delves into the technological and methodological advancements in recommendation systems to promote sustainable tourism behaviours. This includes examining how ML and data-driven recommendation systems can personalise travel experiences to encourage eco-friendly choices and the broader implications of these technologies in fostering a contagion effect of sustainability within the tourism sector. 2.1. Sustainable Tourism and Segmentation With tourism being a significant contributor to economic growth and cultural exchange in the European Union, there is an increasing emphasis on understanding and promoting sustainable tourism practices. Sustainable tourism is an important topic within a broader spectrum of sustainable development. However, the increasing existing research showed its complexity since just a small tiny percentage of the research focuses strictly on sustainability. Roberts et al. (2022) present a meta-analysis of tourism sustainability research highlighting the emergence of new research studies in the field. Thus, it has been recognised that sustainable tourism requires a more critical and comprehensive analysis Butler et al. (2003). Sustainable tourism requires a permanent monitoring of impacts, employing preventive and/or corrective measures or initiatives that aim to reduce environmental impact and support local communities. However, (López-Sánchez and Pulido-Fernández 2016) state that sustainable tourism should focus on the visitors. In this regard, there is increasing empirical literature concerning sustainable tourism segmentation to group tourists using multiple characteristics. By definition, market segmentation is a process of dividing individuals into subgroups based on specific characteristics approaching multiple contexts. A segmentation strategy enables the determination of the number of segments and the classification criteria used for profiling the segment members. The relevance of segmentation is widely acknowledged Tkaczynski et al. (2009), and the literature has proposed many bases to segment tourism markets. In tourism, segmentation profiling has considered geographic, demographic, socioeconomic, psychographic, or behavioural characteristics, as proposed by Kotler and Armstrong (2010). It allows the creation of homogeneous tourist groups, to serve them accordingly and to develop effective tourism policies Mazanec and Dolnicar (2020). With this regard, Bassi and Martín (2024) investigated the willingness of citizens from the 27 EU countries to alter their travel and tourism habits toward more sustainable behaviours, contributing to the recent literature on the interplay between tourism and sustainability. By applying a multilevel analysis to account for the hierarchical structure of the data (citizens within countries), the study identified seven distinct groups of European Adm. Sci. 2024,14, 128 5 of 17 citizens based on their willingness to adopt sustainable tourism practices. These groups were profiled using sociodemographic variables, allowing for a detailed description of typical citizens in each cluster. Mathrani et al. (2023) explored the performance of Asian countries in different dimensions of Sustainable Development Goals (SDGs). Specifically, they proposed a clustering analysis to analyse Asia sustainability, finding that West and South Asian countries perform better than other Asian regions. Similarly, Ça˘glar and Gürler (2022) employed a clustering approach to analyse 110 countries worldwide regarding socioeconomic and politico-cultural structure. Penagos-Londoño et al. (2021) proposed three segments based on economic, sociocultural, and environmental dimensions of perceived sustainability using tourists from Chile and Ecuador, employing a clustering method for segmentation. López-Sánchez and Pulido-Fernández (2016) analysed data from tourists in Western Costa del Sol, Spain, to measure “sustainable intelligence” through latent class analysis. Lastly, Kastenholz et al. (2018) used a scale to assess sustainable travel behaviour at a rural destination, covering environmental, cultural, social, and economic sustainability dimensions. Their hierarchical cluster analysis reveals two segments: active preservers of nature and culture, and local nature, culture, and community seekers. In fact, most segmentation studies in tourism use socio-demographic, psychographic, and behavioural characteristics to segment tourists concerning destination sustainability and trustworthiness (Bassi and Martín 2024;Carvache-Franco et al. 2022;Cooper et al. 2018; Kastenholz et al. 2018;López-Sánchez and Pulido-Fernández 2016;Nickerson et al. 2016). However, according to Tkaczynski et al. (2009), demographic factors are questionable given their low accuracy in predicting actual consumer behaviour, claiming that no research has considered which variables tourism stakeholders use for segmentation. Meanwhile, (Glyptou et al. 2022) have proposed a segmentation approach using different indicators that measure sustainable performance such as environmental footprint, destination dependency on tourism, and locals’ prosperity. Glyptou et al. (2022) analysed Mediterranean countries regarding sustainability to formulate environmental footprint, destination dependency, and locals’ prosperity indicators. 2.2. Recommendations Approaches for Sustainable Tourism Promoting sustainable tourism has become an increasing priority on global agendas due to its environmental, economic, and social implications. In this context, recommendation systems, together with ML techniques, can have an important role in this challenge. Recommendation systems are algorithms designed to suggest relevant items to users. These items can range from products, services, and content to destinations and activities in the context of tourism. Recommendation systems analyse patterns in user behaviour to provide personalised suggestions. They are widely used in e-commerce, streaming services, and social media to enhance user experience by tailoring recommendations to individual needs. Recommendation applications rely on ML, enabling systems to learn and improve from experience without being explicitly programmed. ML algorithms use statistical techniques to identify patterns in data, make predictions, and improve decision-making processes over time. In the context of recommendation systems, ML techniques such as collaborative filtering, content-based filtering, and hybrid approaches are employed to enhance the accuracy and relevance of recommendations Ricci et al. (2011). Collaborative filtering makes recommendations based on the preferences and behaviours of similar users. There are two main types of collaborative filtering: (i) user-based and (ii) item-based. While user-based recommends items that users with similar tastes and preferences liked in the past, item-based recommends items similar to those that the user has liked. In turn, the content-based filtering approach recommends items based on the attributes of the items and the user’s past interactions. For example, if a user likes eco-friendly hotels, the system will recommend other hotels with similar features. It relies on analysing item descriptions and user profiles to match preferences. Finally, hybrid approaches combine collaborative and content-based filtering to leverage the strengths of each method and improve recommendation accuracy. Hybrid systems can use various Adm. Sci. 2024,14, 128 6 of 17 strategies, such as combining the results of both methods or switching between methods depending on the context Fátima Leal et al. (2021). Recommendation systems serve an important role in promoting sustainability by suggesting sustainable activities and less popular destinations to users. These systems utilise ML algorithms to suggest destinations and activities that minimise environmental impact and promote the local economy. Banik et al. (2023) demonstrate that including sustainable options in intelligent suggestions encourages tourists to choose sustainable and less popular areas. Adaji and Adisa (2022) present a review of the use of persuasive technologies to influence sustainable behaviour. The main findings indicate that the majority of applications focus on energy conservation and sustainable food management, leaving a research gap in the domain. In addition, Felfernig et al. (2023) surveyed recommendation systems platforms that support the achievement of the 17 Sustainability Development Goals. The study has identified research issues for sustainability as sustainable evaluation metrics, nudging, contextual explanations, consequence-based explanations, and constraint-based recommendations. In this paper, we employ recommendation systems as a nudge for sustainable tourism, i.e., provoking an intelligent exchange of sustainable tourism habits among EU members. This idea is supported by the empirical literature (Centola et al. 2018; Fieldhouse and Cutts 2012;Partheymüller and Schmitt-Beck 2012;Zorell 2020) concerning health-related behaviours, consumer trends, electoral behaviours, and public opinions, which have revealed that conscious imitation and unconscious contagion of attitudes and behaviours happen across an extensive set of everyday decisions. 2.3. Contributions The literature on tourism sustainability analysis reveals a lack of fundamental studies in EU countries. In this context, this paper contributes a clustering analysis that groups the EU countries into three different clusters using the Eurobarometer survey on the attitudes of Europeans towards tourism. In addition, we propose a sustainability-level approach that rates each country considering their tourist habits. Table 1compares illustrative approaches regarding the sustainable analysis, the countries contemplated, and the representation of the results. As far as we know, none of these approaches offer an analysis of EU member states or a cartographic representation of the results. Although multiple recommendation systems have been developed to promote sustainable tourism, we found a research gap in recommending tourists from countries where sustainability values are deeply developed to less sustainable countries and vice versa. With those recommendation, the main contribution is to create a contagion effect regarding sustainable habits. The contagion effect of sustainable tourism fosters widespread adoption of eco-friendly practices, leading to significant environmental conservation and promoting local cultures and economies Bothos et al. (2015). By encouraging sustainable tourism practices, destinations can create a ripple effect that enhances the tourist experience and ensures long-term benefits for local communities and ecosystems Bothos et al. (2015). Table 1. Comparison of the literature concerning sustainability analysis. Approach Analysis Countries Contagion Effect Bassi and Martín (2024) multilevel latent class EU No Mathrani et al. (2023) clustering Asian No Ça˘glar and Gürler (2022) clustering 110 worldwide No Glyptou et al. (2022) clusters Mediterranean No Penagos-Londoño et al. (2021) clustering Chile and Ecuador No López-Sánchez and Pulido-Fernández (2016) latent class Western Costa Del Sol No Kastenholz et al. (2018) hierarchical cluster Portugal No Our Proposal clustering EU countries Yes statistical Adm. Sci. 2024,14, 128 7 of 17 3. Proposed Method This paper proposes a segmentation of sustainable tourist beliefs from the 27 EU member states and an intelligent exchange of sustainability tourism habits among the EU member states using data from 25,711 participants from the 27 EU member states. The data were collected in October 2021 through the Flash Eurobarometer 499 (GESIS 2022). Figure 1introduces the proposed solution, which encompasses (i) inputs from the Flash Eurobarometer survey on Attitudes of Europeans towards tourism; (ii) a data analysis module; and (iii) a recommendation module. The data analysis module comprises a cluster analysis produced through ML algorithms and, to confirm this segmentation, a country’s tourism sustainability rating was calculated using statistical analysis. Based on this data analysis, a content-based recommendation system is produced to allocate each respondent to the five countries where they can influence or be influenced by the local tourist habits. Figure 1. Recommendations to exchange sustainable culture in EU member states. 3.1. Clustering Analysis The current work employs a clustering approach to analyse the countries in terms of sustainability, considering tourist sustainable habits and the availability of trustworthy sustainable information in tourism destinations. Clustering is an unsupervised ML technique that is used to group similar data points. It aims to identify inherent patterns, structures, or relationships within a dataset. This process involves partitioning a set of objects into subsets, or clusters, where objects within the cluster share common characteristics. Standard clustering methods include k-means clustering, hierarchical, and density-based clustering. Due to its simplicity, efficiency, and interpretability, k-means has been a widely used clustering algorithm. The simplicity and computational efficiency are suitable for large datasets, enabling rapid exploration of clustering solutions. Additionally, k-means produces clusters that are easy to interpret. Moreover, k-means converges quickly, especially with well-chosen initial centroids, making it efficient for practical applications. Furthermore, its availability in widely used ML libraries ensures easy accessibility for researchers. k-means is a widely used clustering algorithm in unsupervised ML. The main goal is to partition a dataset into kclusters, each representing a group of data points with similar characteristics where kstands for the predetermined number of clusters that algorithm detects. To determine the optimal number of clusters, we use the Elbow method. It is a graphical tool used in data analysis that resembles an Elbow, where the optimal number of clusters is situated. The k-means algorithm operates as follows (Hastie et al. 2009): 1. Randomly select kdata points as the initial cluster centroids; 2. Assign each data point to the cluster whose centroid is closest based on distance metrics, e.g., Euclidean distance; 3. Recalculate the clusters’ centroids by taking the mean of all data points assigned to each cluster; 4. Repeat Steps 2 and 3 until convergence, i.e., when the centroids do not suffer changes or when a specified number of iterations is reached. In the present study, we employ k-means to group the 27 EU member-state countries regarding their tourists’ willingness to change travel and tourism habits to become more sustainable and the availability of trustworthy sustainable information in tourism destinations. Adm. Sci. 2024,14, 128 8 of 17 3.2. Level of Tourism Sustainability—Sustainability Rating The definition of a sustainability rating through statistical analysis is another method of grouping countries that validates the clustering methodology presented above and is pursued through ML. This method quantifies the questions using a scale between 1 and 3. Our approach is based on a standard average ( µ ) according to Equation (1) , where qc n indicates the value of the country c of the question n , and C is the total number of countries. Therefore, for both questions, we calculate the standard average ( µ ) considering the number of answers per country, according to Equation (1): µn=1 C C ∑ c=1 qc c(1) Then, to obtain the statistically sustainable level of each question, we calculate the average of the numbers above and below µ , obtaining µ+ and µ− . Finally, a question obtains the statistical level slc qn, according to Equation (2): slc qn=   1 : qc n<µn 2 : µ≤qc n<µ+ n 3 : qc n≥µ+ n (2) The final level is the average of the statistical levels per question, as depicted in Equation (3), where Nis the number of questions: µ=1 N N ∑ n=1 µn(3) 3.3. Content-Based Filtering Content-based filters in recommendation systems match users with items. They create profiles based on past interactions and make recommendations based on the similarity between the users’ content and items, i.e., regardless of other profiles. In this paper, we calculate the similarity among countries and respondents using cosine similarity, as depicted in Equation (4): cos(t,e) = te ∥t∥∥e∥=∑n i=1tiei q∑n i=1(ti)2q∑n i=1(ei)2(4) The cosine similarity corresponds to the cosine of the angle formed between t (profile of the respondent/tourist) and c (profile of the country). The nearer the results approach one, the more appropriate the country is for recommendation. 4. Experiments and Results The experiments use the answers of 25,711 European Union citizens retrieved from the Flash Eurobarometer 499 (GESIS 2022). Specifically, these experiments involve two different data analysis methods to explore the level of sustainability of the EU based on citizens’ travel habits and the availability of trustworthy sustainable information in tourism destinations. While clustering analysis groups the countries in the cluster using k-means, the statistical sustainability level rates the country’s level of sustainability by applying an ordinal scale between 1 and 3. These ordinal scales combined with individual respondents’ profiles are then used to allocate each respondent to a group of countries. 4.1. Dataset The Eurobarometer survey on Attitudes of Europeans towards tourism aims to analyse the long-term impact of COVID-19 on EU citizens concerning travelling behaviours. Furthermore, the survey approaches the importance of sustainability to improve the tourism Adm. Sci. 2024,14, 128 15 of 17 7. Limitation and Future Research Direction Like any study, this one is not without limitations. The results should be interpreted with caution. Despite the large sample, the sizes of the countries and the numbers of respondents in each country are very different, which may have biased the results. Additionally, tourism sustainability was evaluated only by ten items concerning travel and tourism habits and by five items evaluating the availability of information, which is certainly insufficient to assess sustainability. Furthermore, the countries are economically and culturally very different from each other, which undoubtedly impacts the results. Finally, our recommendation process needs to be confirmed and tested. It is our contention that these drawbacks are overcome by the contribution of this study. In follow-up research, it would be useful to more specifically investigate and evaluate the relevance of applying a mobile device that traces the behavioural contagion effect left by the tourists in their tourism experience. It would also be interesting to introduce demographic data in the individual profiles to refine the results and provide better recommendations. We intend to follow this investigation shortly. Future studies concerning tourist sustainability convergence among EU member states should consider their cultural and economic differences. Finally, the data of the Flash Eurobarometer 499 were collected during 2021, when many Europeans were unable to travel or, if they did so, with many restrictions. Therefore, it will be necessary to repeat the interviews in order to compare the 2021 results with the current ones, focusing on a series of questions about the real habits of the consumer as a tourist. Author Contributions: Conceptualisation, F.L. and M.P.; methodology, F.L. and M.P.; validation, F.L. and M.P.; formal analysis, F.L. and M.P.; investigation, F.L. and M.P.; resources, F.L. and M.P.; data curation, F.L. and M.P.; writing—original draft preparation, F.L. and M.P.; writing—review and editing, F.L. and M.P.; visualisation, F.L. and M.P.; supervision, F.L. and M.P.; project administration, F.L. and M.P.; funding acquisition, F.L. and M.P. All authors have read and agreed to the published version of the manuscript. Funding: This work was funded by the Interreg Spain-Portugal (POCTEP) 2021-2027 programme, cofunded by the European Union, under the Twin NavAux project, 0070_TWIN_NAV_AUX_1_E. Institutional Review Board Statement: Not applicable. Informed Consent Statement: Not applicable. Data Availability Statement: The data presented in this study are available on request from the corresponding author. Conflicts of Interest: The authors declare no conflicts of interest. Abbreviations The following abbreviations are used in this manuscript: SDG Sustainable Development Goal EU European Union ML Machine Learning References Adaji, Ifeoma, and Mikhail Adisa. 2022. A review of the use of persuasive technologies to influence sustainable behaviour. Paper presented at Adjunct Proceedings of the 30th ACM Conference on User Modeling, Adaptation and Personalization, Barcelona, Spain, July 4–7; pp. 317–25. Axhami, Mirdaim, Valentina Ndou, Veronica Milo, and Paola Scorrano. 2023. Creating value via the circular economy: Practices in the tourism sector. Administrative Sciences 13: 166. [CrossRef] Banik, Paromita, Ashmi Banerjee, and Wolfgang Wörndl. 2023. Understanding user perspectives on sustainability and fairness in tourism recommender systems. Paper presented at Adjunct Proceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization, UMAP ’23 Adjunct, New York, NY, USA, June 26–29; New York: Association for Computing Machinery, pp. 241–48. [CrossRef] Adm. Sci. 2024,14, 128 16 of 17 Bassi, Francesca. 2023. European consumers’ attitudes towards the environment and sustainable behavior in the market. Sustainability 15: 1666. [CrossRef] Bassi, Francesca, and Juan Antonio Marmolejo Martín. 2024. Drivers of sustainable tourism in europe: How to design efficient business strategies. Quality & Quantity 1–26. [CrossRef] Bothos, Efthimios, Dimitris Apostolou, and Gregoris Mentzas. 2015. Recommender systems for nudging commuters towards eco-friendly decisions. Intelligent Decision Technologies 9: 295–306. [CrossRef] Butler, David, Paul Jowitt, Richard Ashley, David Blackwood, John Davies, Crina Oltean-Dumbrava, G. McIlkenny, T. Foxon, D. Gilmour, H. Smith, and et al. 2003 Sward: Decision support processes for the uk water industry. Management of Environmental Quality: An International Journal 14: 444–59. [CrossRef] Carvache-Franco, Mauricio, Conrado Carrascosa-López, and Wilmer Carvache-Franco. 2022. Market segmentation by motivations in ecotourism: Application in the posets-maladeta natural park, spain. Sustainability 14: 4892. [CrossRef] Centola, Damon, Joshua Becker, Devon Brackbill, and Andrea Baronchelli. 2018. Experimental evidence for tipping points in social convention. Science 360: 1116–19. [CrossRef] Cooper, Chris, Serena Volo, William C. Gartner, and Noel Scott. 2018. The SAGE Handbook of Tourism Management: Theories, Concepts and Disciplinary Approaches to Tourism. Thousand Oaks: SAGE. [CrossRef] Ça˘glar, Mehmet, and Cem Gürler. 2022. Sustainable development goals: A cluster analysis of worldwide countries. Environment, Development and Sustainability 24: 8593–624. [CrossRef] de Bruyn, Chané, Foued Ben Said, Natanya Meyer, and Mohammad Soliman. 2023. Research in tourism sustainability: A comprehensive bibliometric analysis from 1990 to 2022. Heliyon 9: e18874. [CrossRef] Dias, Francisco Teixeira Pinto, Sara Maria Rodrigues Góis, and Gonçalo Nuno de Castro Oliveira Gomes. 2023. Tourism monitoring as a strategic tool for tourism management: The perceptions of entrepreneurs from centro de portugal. Administrative Sciences 13: 205. [CrossRef] Dolnicar, Sara. 2006. Nature-conserving tourists: The need for a broader perspective. Anatolia 17: 235–55. [CrossRef] Eurostat. 2023. Travel, Torism & Hospitality. London: World Travel & Tourism Council. Felfernig, Alexander, Manfred Wundara, Thi Ngoc Trang Tran, Seda Polat-Erdeniz, Sebastian Lubos, Merfat El Mansi, Damian Garber, and Viet-Man Le. 2023. Recommender systems for sustainability: Overview and research issues. Frontiers in Big Data 6: 1284511. [CrossRef] Fieldhouse, Edward, and David Cutts. 2012. The companion effect: Household and local context and the turnout of young people. The Journal of Politics 74: 856–69. [CrossRef] Florido, Carmen, Marta Jacob, and Margarita Payeras. 2019. How to carry out the transition towards a more circular tourist activity in the hotel sector. the role of innovation. Administrative Sciences 9: 47. [CrossRef] Fátima Leal, Benedita Malheiro, Bruno Veloso, and Juan Carlos Burguillo. 2021. Responsible processing of crowdsourced tourism data. Journal of Sustainable Tourism 29: 774–94. [CrossRef] GESIS. 2022. Flash Eurobarometer 499 (Attitudes of Europeans towards Tourism, Autumn 2021). Available online: https: //search.gesis.org/research_data/ZA7807 (accessed on 25 April 2024). Glyptou, Kyriaki, Nikos Kalogeras, Dimitrios Skuras, and Ioannis Spilanis. 2022. Clustering sustainable destinations: Empirical evidence from selected mediterranean countries. Sustainability 14: 5507. [CrossRef] Hastie, Trevor, Robert Tibshirani, Jerome Friedman, Trevor Hastie, Robert Tibshirani, and Jerome Friedman. 2009. Unsupervised learning. In The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Berlin: Springer, pp. 485–585. [CrossRef] Holmes, Mark Robert, Rachel Dodds, and Isabelle Frochot. 2021. At home or abroad, does our behavior change? Examining how everyday behavior influences sustainable travel behavior and tourist clusters. Journal of Travel Research 60: 102–16. [CrossRef] Jarvie, Michelle E. 2016. Brundtland Report. Available online: https://www.britannica.com/topic/Brundtland-Report (accessed on 25 April 2024). Kastenholz, Elisabeth, Celeste Eusébio, and Maria João Carneiro. 2018. Segmenting the rural tourist market by sustainable travel behaviour: Insights from village visitors in portugal. Journal of Destination Marketing & Management 10: 132–42. [CrossRef] Kotler, Philip, and Gary Armstrong. 2010. Principles of Marketing. London: Pearson Education. Li, Qiucheng, and Maoying Wu. 2020. Tourists’ pro-environmental behaviour in travel destinations: Benchmarking the power of social interaction and individual attitude. Journal of Sustainable Tourism 28: 1371–89. [CrossRef] Liu, Chui-Hua, Gwo-Hshiung Tzeng, Ming-Huei Lee, and Po-Yen Lee. 2013. Improving metro–airport connection service for tourism development: Using hybrid mcdm models. Tourism Management Perspectives 6: 95–107. [CrossRef] Liu, Yan, Xinyue Cao, and Xavier Font. 2024. Nudge pro-environmental contagion: Residents to tourists. Annals of Tourism Research 105: 103738. [CrossRef] López-Sánchez, Yaiza, and Juan Ignacio Pulido-Fernández. 2016. In search of the pro-sustainable tourist: A segmentation based on the tourist “sustainable intelligence”. Tourism Management Perspectives 17: 59–71. [CrossRef] Mathrani, Anuradha, Jian Wang, Ding Li, and Xuanzhen Zhang. 2023. Clustering analysis on sustainable development goal indicators for forty-five asian countries. Science 5: 14. [CrossRef] Mazanec, Josef A., and Sara Dolnicar. 2020. Segmentation—Tourism. Cham: Springer International Publishing, pp. 1–4. [CrossRef] Nash, Dennision, and Richard Butler 1990. Towards sustainable tourism. Tourism Management 11: 263–64. [CrossRef] Adm. Sci. 2024,14, 128 17 of 17 United Nations. 2015. Transforming Our World: The 2030 Agenda for Sustainable Development. New York: United Nations. Available online: www.un.org/en/development/desa/population/migration/generalassembly/docs/globalcompact/A_RES_70_1_E.pdf (accessed on 25 April 2024). Nickerson, Norma Polovitz, Jake Jorgenson, and B. Bynum Boley. 2016. Are sustainable tourists a higher spending market? Tourism Management 54: 170–77. [CrossRef] O’Mahony, C., M. Ferreira, Y. Fernandez-Palacios, V. Cummins, and R. Haroun. 2009. Data availability and accessibility for sustainable tourism: An assessment involving different european coastal tourism destinations. Journal of Coastal Research 1135–39. Organization World Tourism, and International Transport Forum. 2019. Transport-Related CO 2 Emissions of the Tourism Sector—Modelling Results. Madrid: UNWTO. [CrossRef] Park, Duk-Byeong, and Yoo-Shik Yoon. 2009. Segmentation by motivation in rural tourism: A korean case study. Tourism Management 30: 99–108. [CrossRef] Partheymüller, Julia, and Rüdiger Schmitt-Beck. 2012. A “social logic” of demobilization: The influence of political discussants on electoral participation at the 2009 german federal election. Journal of Elections, Public Opinion & Parties 22: 457–78. [CrossRef] Penagos-Londoño, Gabriel I., Carla Rodriguez-Sanchez, Felipe Ruiz-Moreno, and Eduardo Torres. 2021. A machine learning approach to segmentation of tourists based on perceived destination sustainability and trustworthiness. Journal of Destination Marketing & Management 19: 100532. [CrossRef] Poortinga, Wouter, Lorraine Whitmarsh, Linda Steg, Gisela Böhm, and Stephen Fisher. 2019. Climate change perceptions and their individual-level determinants: A cross-european analysis. Global Environmental Change 55: 25–35. [CrossRef] Pronello, Cristina, and Jean-Baptiste Gaborieau. 2018. Engaging in pro-environment travel behaviour research from a psycho-social perspective: A review of behavioural variables and theories. Sustainability 10: 2412. [CrossRef] Ricci, Francesco, Lior Rokach, and Bracha Shapira. 2011. Introduction to Recommender Systems Handbook. Boston: Springer US, pp. 1–35. [CrossRef] Roberts, Chris, Joel Reynolds, and Mary Jo Dolasinski. 2022. Meta-analysis of tourism sustainability research: 2019–2021. Sustainability 14: 3303. [CrossRef] Rokach, Lior, and Oded Maimon. 2005. Clustering methods. In Data Mining and Knowledge Discovery Handbook. Boston: Springer, pp. 321–52. [CrossRef] Streimikiene, Dalia, Biruta Svagzdiene, Edmundas Jasinskas, and Arturas Simanavicius. 2021. Sustainable tourism development and competitiveness: The systematic literature review. Sustainable Development 29: 259–71. [CrossRef] Su, Lujun, Jin Cheng, Jun Wen, Metin Kozak, and Stephen Teo. 2022. Does seeing deviant other-tourist behavior matter? The moderating role of travel companions. Tourism Management 88: 104434. [CrossRef] Tang, Haiyan, Yong Ma, and Jie Ren. 2022. Influencing factors and mechanism of tourists’ pro-environmental behavior–empirical analysis of the cac-moa integration model. Frontiers in Psychology 13: 1060404. [CrossRef] Tkaczynski, Aaron, Sharyn R. Rundle-Thiele, and Narelle Beaumont. 2009. Segmentation: A tourism stakeholder view. Tourism Management 30: 169–75. [CrossRef] Wu, Jialin (Snow), Xavier Font, and Jingyan Liu. 2021. Tourists’ pro-environmental behaviors: Moral obligation or disengagement? Journal of Travel Research 60: 735–48. [CrossRef] Yang, Yuetao, Gowhar Ahmad Wani, Velayutham Nagaraj, Mohammad Haseeb, Sameer Sultan, Md. Emran Hossain, Mustafa Kamal, and Syed Mehmood Raza Shah. 2023. Progress in sustainable tourism research: An analysis of the comprehensive literature and future research directions. Sustainability 15: 2755. [CrossRef] Zorell, Carolin V. 2020. Nudges, norms, or just contagion? A theory on influences on the practice of (non-)sustainable behavior. Sustainability 12: 418. [CrossRef] Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.