Information and Communication Technologies in Tourism 2018

The technological developments regarding Virtual Reality (VR) are providing new opportunities for the tourism industry. This research investigates the application of fully-immersive VR systems in tourism marketing and analyses how it influences emotional responses and decision-making. During a laboratory experiment, subjective measurements were combined with physiological measurements of arousal. Study participants were exposed to a 360-degree destination marketing video, using either a head-mounted display (HMD) or a desktop-PC. Whereas the physiological parameters of heart rate and electrodermal activity showed a significant increase with the HMD-group, subjective evaluation of emotions and decision-making did not indicate any significant differences. These partly contradicting results suggest further investigation of emotions and arousal measurement, analysis and interpretation through field experiments. Nevertheless, from subjective opinions of participants and participant observations it could be concluded that VR as a marketing tool has the potential to increase positive emotions. Taken the enthusiasm and interest for VR in tourism into account, recommendations concerning investment in VR technology are given.

This research will take PokemonGo, as a case of a location-based augmented reality (AR) mobile game, and explore the existence of its links to tourism. By illuminating the aspect of AR mobile games which wholly immerse with the real geographic space, the study attempts to categorize the immersion environment into two constructs, reality (offline) and virtual (online). In addition, based on balance theory the study model examines the relationship between destination satisfaction and game play satisfaction. The hypotheses were tested using 228 Korean PokemonGo players who had experience in visiting a location to play the game. The findings show AR immersion can be a combination of two dimensions and game play satisfaction has a positive effect on destination satisfaction. Thus identifying AR mobile game’s potentially influence tourism behaviour.

Regarding the growing importance of the peer-to-peer online travel marketplace and lack of understanding on it, this study aims to investigate how different types of travellers use peer-to-peer online travel marketplaces in distinctive ways. Different traveller behaviours are measured using six factors from twenty items. 2467 survey respondents were combined with real transaction data. We identify six idiosyncratic groups of travellers. They are named Shopaholic, Budget Explore, Long-Term Traveller, Trend Setter, Resort Addict, and Social Tripper. Those groups are different in several aspects, such as demographic characteristics. More importantly, the results show their usage of the online tourism marketplace is significantly different. Our study contributes to the literature on traveller segmentation through an exploration of their different usage of online travel services. It also provides practical insights, especially for marketplace operators and travel product providers.

The aim of this paper is to investigate the factors which influence the probability of an Airbnb property being booked using the properties in London as an example. A binomial logistic model is estimated by sequential Bayesian updating due to the large volume of the data. The results show that, in spite of the market factors revealing great influence, the attributes of the properties play a more important role in influencing the booking probability of the properties. These research findings are potentially beneficial to both the Airbnb practitioners and the industrial organizers.

Rooted in the Sustainable Livelihood Approach, this paper contributes to the current debate on e-tourism for development by analysing the use of ICTs in community-based tourism micro enterprises. Using a qualitative case study approach with semi structured interviews, observations and documentary evidence, this study sheds light on the importance of ICTs in homestays and analyses its impact on the five livelihood assets (i.e. human, natural, financial, physical, social) as perceived by Malaysian homestay managers. Results indicate that there are significant direct and indirect impacts of ICTs on the livelihood assets of the community and open the floor for further research in the field.

Crowdsourcing strategies that harness the collective energy and creativity of large numbers of contributors are useful to create social innovation. While the number of crowdsourcing social innovation platforms is increasing, many fail to engage a critical mass of users who are both willing and capable to participate in value co-creation. To address this shortcoming, a 6-year action research project was conducted to study the design of crowdsourcing platforms for social innovation in the tourism industry. In two action research cycles involving numerous data collection strategies and interventions, a crowdsourcing platform called travel2change was created, deployed, evaluated, and improved. The study reveals a set of design principles for crowdsourcing social innovation platforms and enriches research on crowdsourcing to fit the social innovation context. Practitioners receive helpful insights to leverage crowdsourcing for social innovation.

Tourism is one of today’s most relevant industries. It is a data intensive, complex sector that can involve various stakeholders, services and technologies in varying proportions and on different scales. ICT plays a key role in supporting tourism. In this paper we focus on ICT as a key enabler for effective information exchange and provision of value-added services to end-users, and we discuss how tourism can benefit from digital ecosystems as a means for creating relationship environments of stakeholders from both the public and the private sector. In particular, we present a selection of tourism-oriented end-user applications enabled by the E015 Digital Ecosystem operating in Italy since 2013.

The inbound tourism industry keeps growing in recent years. Affected by the factors such as education, culture and geographic conditions, people from different countries may have different preferences and attitudes towards tourism products. Thus, it is important to understand the need of people from different countries to develop an effective and targeted promotion and marketing strategy. This research aims to develop a method to extract the needs of tourists from different countries from travel reviews. In this paper, both manual analysis and basic text-mining techniques are used to explore the content of reviews posted by tourists from six different countries, written in English, Japanese and Chinese from TripAdvisor.

Travel planning is highly reliant on the websites of tourist bureaus, professional travel writers and experienced (non-professional) travelers. This study examines the search preferences of Chinese speaking Generation Z (alternatively known as Post-Millennials, the iGeneration, Founders, Plurals, or the Homeland Generation) as they plan a trip to a destination unfamiliar to them. The findings indicated more than 70% of the websites they frequented were well-known international sites, including user generated content (UGC) and the sites of business entities. The sites most preferred by Generation Z were UGC websites, with 100% of the participants saying they frequently use them while travel planning. The Destination Management Office (DMO) website was not a popular source, being frequently used by only 13% of participants. Of the nine dimensions of destination information, the two rated most important were natural resources and natural environment, which suggests that travel planners strongly associate Kenya with these qualities. Leisure and recreation information ranked least important. The results indicate, firstly, the perceived destination image affects the perceived importance of the destination information, and secondly, with the exception of popular world-wide travel websites, travelers prefer using local sites which share the same language and cultural background.

Food is widely recognized as an important attribute that attracts tourists to a particular destination. Drawing on data related to the online reviews of U.S. tourists on ethnic restaurants in Hong Kong, this study presents the first attempt to identify tourists’ restaurant selection patterns at destinations by applying the association rule mining technique. Results of this study show that most U.S. tourists have tried Cantonese food while in Hong Kong. Japanese, Asian Fusion, Shanghainese and Taiwanese cuisines are found to be substituting alternatives to Cantonese cuisines, as tourist review patterns reveal negative relationships between them and ethnic Cantonese restaurants. A portion of U.S. tourists exhibit food neophobic behaviours as they appear to be reluctant to try Cantonese cuisines and stick to their own food instead. Given these findings, practical implications are provided for destination marketing oganisations.

The evolution of information and communication technology now makes it possible to collect travel information in a variety of ways. Social media content that includes blogs is one such useful information source when planning a trip. In this study, we propose a method for generating a summary of multiple travel blog entries that contain images. Our method identifies significant sentences in addition to the images by using a graph-based approach that takes account of travelers’ types of behavior. To investigate the effectiveness of our method, we conducted experiments, which demonstrated that our method can outperform some baseline methods. We also implemented a system for generating summaries based on our method.

This paper presents a systematic review of 74 academic journal articles investigating the theoretical models and determinants of the acceptance and adoption of ICTs within the etourism framework. The most widely used theoretical models of technology acceptance are identified and critically discussed. Furthermore, a synthesis of the most widely reported determinants of technology adoption is provided to illustrate a systematic categorisation of the determinants of the acceptance of new tourism and hospitality technologies. Synthesising these findings provides etourism academia with a summarised, yet comprehensive understanding of the well-established aspects of technology acceptance and invites researchers to shift their attention towards using other methods of inquiry to investigate those aspects of technology acceptance behaviour which remain to be understood.

Communication through social media is an effective way to position a destination brand. In particular, the emotional values of a brand trigger a positive reaction from potential visitors. It is important for destinations to align their emotional communication strategies on different social media platforms to enhance their online image. The lack of comprehensive research in this area led this study to analyse the usage of the two most used social media platforms (Facebook and Twitter) among popular European tourist destinations. The study shows how destinations communicate their emotional values differently in Facebook and Twitter. The methodology of analysis allows destinations to compare the values they communicate with those of their competitors, so that they can improve their positioning and present a distinctive attractive personality of their destination.

Online marketing strategies are an important part of any destination promotion agenda. DMOs use Facebook to engage with various stakeholders and enhance their image. Given the benefits of this approach, destination managers often are not guided or well informed about success strategies to maintain their Facebook brand pages and effectively communicate, engage and enhance their relationships with their consumers. The lack of empirical longitudinal research led this study to perform a retrospective analysis of the Facebook pages of the 22 most popular tourist destinations in Europe according to TripAdvisor 2017 rankings. The data-driven approach demonstrates which marketing activities triggered various consumer engagement behaviour and, thus, are successful in Facebook spheres. Furthermore, the study allows destinations to benchmark their Facebook presence and position themselves more strategically.

Alpine regions are valued for their natural treasures by both tourists and locals alike. In order to preserve their natural resources, higher awareness and practical solutions towards sustainability in general and—especially in the region of Tyrol in Austria—sustainable mobility are in high demand. To foster such awareness, social media offers great possibilities for communication and interaction via online communities, and a strategic employment of such tools could amplify the adoption of a more sustainable travel behaviour among people. A quantitative study, employing the Theory of Planned Behaviour, the influence of attitude, subjective norm and control factors on the behavioural intention to travel more sustainably, moderated by a person’s engagement on social media with sustainability topics, was applied. Results show a positive relation of sustainable attitude, subjective norm and perceived behavioural control towards the intention to travel more sustainably. Over and above, the outcome discloses the impact of individuals’ social media engagement on their behavioural intention. Thus, social media strategies can lead to an intended change in behaviour and foster sustainable mobility.

By combining perceived online social capital and the Elaboration Likelihood Model (ELM) of persuasion, this study constructed an integrated model to explore the antecedents and consequences of online social capital in travel information engagement on social media. Data (N = 578) were collected through Web-based survey and paper-and-pencil survey in China. Results of Structural Equation Modelling (SEM) supported that both bridging and bonding social capital contributed significantly positive effects to consumer engagement on social media. The two forms of social capital were positively influenced by argument quality and perceived information usefulness. Source credibility positively affected bonding social capital but had no effect on bridging social capital. The findings also show that bridging social capital is more effective in predicting consumer engagement than bonding social capital.

This research identifies two types of review patterns, authentic and fake, based on configurations among reviewers and review content elements. We also explain what fake review is with IMT as theoretic background. The results, which are based on the fsQCA method, identify the combinations of configurations for authentic and fake reviews. Each pattern has unique characteristics. Authentic reviews’ patterns are explained by personality theory (i.e., five factor model). Authentic reviews represent personalities that are different, similar to individuals, while fake reviews are composed of three kinds of promotional reviews and are characterized by a reviewer’s low credibility. The fake review pattern is explained by HSM and ELM. This research confirms that different patterns seem to exist for authentic and fake reviews, although authentic reviews may be cited in reverse fake reviews via algorithms. Another finding is that the review business has expanded to the business of social networking.

Despite major and ongoing strides in sustainability research, food remains an under-researched area in tourism. Food plays an important and often contradictory tourism role, with positive personal experiences and negative sustainability consequences. This conceptual paper encourages dialog and begins a new sustainable tourism research stream exploring the intersections among household food waste, tourism and social media. The paper proposes four research agenda items and possible future research ideas. The findings give academics and practitioners practical and theoretical insights and implications for current and future ways, such as social media, to address household food waste in tourism.

Online travel reviews are paramount to trip planning because they help consumers’ form images of destinations. Despite ample studies on hotel service attributes, knowledge is scarce regarding culturally nuanced attributes, including security perceptions. This study examines consumers’ perceptions of service attributes and security/safety concerns of hotels in Africa. Data were extracted from three hotel categories (3, 4, and 5-stars), which were based on TripAdvisor rankings from Egypt, Ghana, Kenya, Nigeria, and South Africa. A hybrid analysis revealed that hotel service attributes and security/safety are cardinal evaluation criteria for visitors to Africa. Additionally, our study reveals that most negative reviews were from 5-star hotels and Egypt received more positive reviews in all the service attributes than other countries.

Branding has shifted from brand as a resource owned by the firm to brand as a collaborative activity co-created by the firm and its stakeholders. Using a single case study approach, this paper uses Marriott Hotels International, to explore how Web 2.0 has transformed the landscape of brand management. It aims to uncover how co-creation of brand value is being carried out between companies and consumers through social media. Wide-ranging secondary research data was reviewed and semi-structured interviews were conducted with Marriott managers. Findings suggest that past marketing and branding mantras of consistency and control are no longer relevant. Companies can co-create brand value by adopting a strategy that incorporates brand communities, brand stories and influencers in the co-creation of their brand narrative, in real time. This study contributes to furthering the understanding of branding theory and practice in the age of Web 2.0 and will be useful to managers in formulating future branding strategies and building their competitiveness.

Social media have transformed the hospitality and tourism industry and affected how customers interact and take decisions, but have also affected organisations’ business strategies and processes. Prior research has shown that a key understanding of IT implementation in organisations is how individuals adopt, use and make sense of technologies. Despite the increased use of social media in hotel organisations there is a research gap and little is known about how individuals’ sense-making affects organisational use over time. The aim of the present study is to contribute to the research field by using Orlikowski and Gash’s (ACM Trans Inf Syst 12(2):174–207, 1994) framework of Technological Frames. The interpretative case study follows social media use in 14 hotel organisations within an international hotel chain in seven European countries over four years. The study finds incongruence and lack of dominant frames and discusses the related organisational implications.

Real-time service has gained higher importance as part of the digital competitiveness of brands. This has followed the establishment of social media as an engagement mechanism that supports consumer experience by bridging consumer expectations and brand performance in real time. The ubiquity of social media’s constant connectivity has led to the increasing demand of instant gratification. Consumers not only demand brands to provide a personalised response, but also expect them to reply instantly ‘now’. This exploratory research aims to identify how brands leverage social media and technology to enhance consumer experience in real-time. Data collection was conducted in two research stages. First an in-depth case study of Marriott MLive and then multiple case studies of four best-practice companies. Real-time data monitoring and engagement can support organisations to eliminate problems before they escalate, enhance customer experience and also take advantage of upselling opportunities. This study concludes with a real-time service competitive advantage conceptual framework. The findings suggest that the integration of real-time listening and monitoring in conjunction with highly contextual delivery become crucial tools for enhancing brands competitiveness.

The means of computer-mediated communications continue to evolve along with the rapid development of IT. Realizing the importance of maintaining a close relationship with customers, hospitality organizations have started adopting new media such as Instant Messaging (IM) applications to communicate with customers. Customers’ intention to adopt IM to communicate with hotels are remained unknown. This study explores factors influencing customers’ intention to use IM to communicate with hotels based on the technology acceptance model and computer-mediated communication theories. Using an experimental design, online survey and nested logistic regression analysis, the findings reveal that age and perceived usefulness of IM exert substantial influence on customers’ intention to use IM for hotel-customer communication. This study provides several theoretical and practical implications.

In light of the trend in integrating artificial intelligence and robotics into tourism and hospitality operations, it is important to understand consumer responses to hotel service robots. Two studies were conducted to achieve this objective: an online survey and a laboratory experiment using measurements of automatic emotional reactions via biosensors. Responses to two types of robots, NAO for check-in and Relay for room delivery, were tested. Study 1 demonstrates that consumer intention to adopt hotel service robots is influenced by human-robot interaction dimensions of anthropomorphism, perceived intelligence, and perceived security. Differences were found between NAO and Relay: NAO’s adoption depends on anthropomorphism and perceived security, while Relay’s on perceived intelligence and importance of service operation in hotel experiences. Study 2 revealed support for the importance of anthropomorphism and perceived security in NAO, as reflected in Galvanic Skin Response (GSR) peaks during sequences of interactions and fixation on NAO’s face. Support for perceived intelligence in Relay was also identified. Implications for the hospitality industry are provided.

Consumers are increasingly adopting mobile apps to make hotel reservations. Apart from attracting new users, hoteliers and Online Travel Agents (OTAs) devote great efforts to motivate customers’ continuous use of the apps. This study introduces Implicit Theories of Intelligence (ITI) as an antecedent of the intention to continue the use of apps and explores the underlying mechanism. This study draws from an online survey administered to 459 Chinese respondents to link ITI with continuance intention (CI). The findings show that incremental theorists of intelligence exhibited higher hedonic motivation (HM) and lower perceived risk (PR) in the use of apps than entity theorists of intelligence. HM positively predicted CI, whereas PR negatively predicted CI. Contrary to our expectation, the mediating role of effort expectancy was not supported. These findings offer meaningful implications to hoteliers and OTAs.

Information and communication technology has evolved over the past two decades, particularly in the recent five years. Along with the extensive use of smartphones, mobile payment has emerged as an innovation of the age. At present, Chinese people heavily rely on mobile payment in their daily lives and their travels. Nevertheless, what if mobile payment breaks down during their use? To address this issue, this study focuses on the pre-crisis management stage (i.e., awareness and flexibility) of the crisis management framework to detect the potential breakdown of mobile payment systems. Findings indicate that during their travel, travelers tend to use bank cards or mobile payment more than they use cash. Moreover, attributes for measuring awareness and flexibility are identified through principal component analysis. Results of this study could assist tourism practitioners in understanding the current situation of adopting mobile payment among Chinese travelers and preparing for the potential breakdown of mobile payment.

The Internet of Things (IoT) enables new ways for exploiting the synergy between the physical and the digital world and therefore promises a more direct and active interaction between tourists and local products and places. In this article we show how, by distributing sensors/actuators in the environment or attaching them to objects, one can sense, trace and respond to users’ actions onsite. Our research method analysis specific scenarios (case studies) of tangible interaction. We first discuss important issues, which were identified in these scenarios, and are related to log analysis, system usability, and extended models for learning user preferences. Then, the lessons learned in these specific cases have informed the constructive design of a wider scope infrastructure, which is here described and motivated. We envisage the tight integration of localized IoT solutions into a comprehensive mobile information system for tourism.

Review platforms are gaining more and more importance in the tourism industry. From a consumer’s point of view, reviews facilitate information search and influence the decision making process. Service providers are unable to neglect the impact of such websites and are thus forced to track reviews. However, due to the massive load of reviews, this task becomes more and more time consuming. Text mining tools assist in extracting decision-relevant knowledge from user-generated content (UGC). In order to assess the appropriateness of machine-driven approaches, TripAdvisor reviews of restaurants as well as hotels were collected and analysed applying the AYLIEN Text Analysis API on RapidMiner. The conclusions hereof were then compared with results generated by traditional manual content analysis. Findings support the adequacy of fully automated domain specific aspect-based sentiment analysis tools. The authors argue that the suggested methodology facilitates the analysis dramatically and can thus be simply applied on a regular basis with the aim to constantly monitor reviews.

Due to the perishable nature of tourism services and the limited capacity of tourism firms in serving customers, accurate forecasts of tourism demand are of utmost relevance for the success of tourism businesses. Nowadays, travellers extensively search the web to form expectations and to base their travel decision before visiting a destination. This study presents a novel approach that extends autoregressive forecasting models by considering travellers’ web search behaviour as additional input for predicting tourist arrivals. More precisely, the study presents a method with the capacity to identify relevant search terms and time lags (i.e. time difference between web search activities and corresponding tourist arrivals), and to aggregate these time series into an overall web search index with maximal effect on tourism arrivals. The study is conducted at the leading Swedish mountain destination, Åre, using arrival data and Google web search data for the period 2005–2012. Findings demonstrate the ability of the proposed approach to outperform traditional autoregressive approaches, thus, to increase the predictive power in forecasting tourism demand.

Photos have been an important means to transfer destination image to potential travelers, as they are widely available on travel related web sites. However, there has been very limited attempt to assess visual quality of online photos, which plays an important role in influencing traveler emotion and their travel intention. This is probably due to the limited background in photography among tourism researchers, and the inefficiency of manual assessment approach. Aiming to overcome these barriers, this paper presents a computational approach to visual features extraction for automatic photo quality assessment. We describe a number of visual features, which are helpful in reflecting the photo quality, and then validate their performance through a number of experiments using a large-scale data set of online travel photos. The introduced approach has the potential to facilitate the evaluation of visual quality of photos on travel web sites and online travel photos.

The amount of people using online platforms to book a travel accommodation has grown tremendously. Hence, tour operators implement recommender systems to offer most suitable hotels to their customers. In this paper, a method of using hotel descriptions for recommendation is introduced. Different natural language processing methods were applied to pre-process a corpus of hotel descriptions. Further, three machine learning approaches for the allocation of hotel descriptions to travel behavioural patterns were implemented: clustering, classification and a dictionary-based approach. The main results show that clustering cannot be used in this context since the algorithm mostly relies on the operator-dependent structure of the descriptions. Supervised classification achieves the highest precision for six travel patterns, whereas the dictionary approach works best for one pattern. In general, the results for the different travel patterns vary due to the unequally distributed data sets as well as various characteristics of the patterns.

Tourism is an information intensive domain, where recommender systems have become an essential tool to guide customers to the right products. However, they are facing major challenges, since tourism products are considered as complex and emotional. It has been shown that the seven-factor model is a legitimate way to counter some of these challenges. However, in order to recommend an item, it has also to be described in terms of this model. This work’s aim is to find a scalable way to map tourism destinations, defined by their attributes, to the seven-factor model. Through statistical analysis and learning methods it is shown that there is a significant relationship between particular destination features and the seven-factors and that destinations can be grouped in a meaningful way using their attributes.

‘Smart tourism’ and ‘smart tourism destinations’ (STDs) have become commonplace in the research of the interrelationship between tourism, destinations and the latest Information and Communication Technologies (ICTs). However, research has failed hitherto to identify if this evolution towards smartness of tourism is accompanied by a similar process in tourism education to provide the system with prepared human resources once the transformation has been fully completed. This paper aims to fulfil this gap, by taking the case of Spanish public superior education in tourism, to analyse in which degree ICTs, as critical knowledge and skills required within STDs, are included in tourism curricula and how students assess the formation they receive in this regard. The analysis offers several valuable implications for governments in charge of public education design and opens discussion over the possibility to strengthen the technological side of tourism curricula.

Despite the increasing popularity of eLearning courses about tourism destinations, research on how they should be designed and what makes them usable in the eyes of the travel trade remains scarce. Trying to fill this gap, the main aim of this research is to find a suitable framework for evaluating online courses about tourism destinations. To do so, the creation process of the Switzerland Travel Academy by Switzerland Tourism is presented with a focus on evaluating not only the platform’s usability, but also its impact on travel agents’ knowledge about, and involvement with the tourism destination after the completion of the course. The proposed framework enhances the theoretical foundation in the eLearning domain, as well as might be used within practical developments of eLearning courses not only by tourism destinations, but also by other eLearning product developers.

This research proposes a framework of intergenerational learning (IGL) that supports child-to-parent influence in the context of heritage learning using augmented reality (AR) and serious game applications. Positioning children as the behavioural catalysts in the learning process, the framework is developed based on several considerations and requirements. First, the technologies are designed to play a role in attracting and engaging children in learning and providing an intergenerational participation structure to allow children to influence parents’ attitudes and behaviour. Second, using the mechanics, dynamics, and aesthetics framework of game design, the game elements are designed to provide realistic context for experiential learning, informative guiding and player interactions to increase engagement, as well as clear and measurable success indicators to increase motivation. The outcome of this framework is attitude and behaviour change in children and parents with regards to heritage preservation and appreciation, which is one of the main goals of heritage tourism managers.

Eyetracking research has gained traction in a wide range of contexts and finds increasing application in the travel and tourism domain. Whilst there exists some empirical evidence of eyetracking in tourism, most research to date is restricted to lab environments and desktop computers, or occurs on a small scale. This paper presents a first large-scale mobile eyetracking study through a multiple-stage research design that focuses on the visitor’s interactive learning experience in a real-life museum context. Based on an emic visitor perspective, the findings unlock insights into a range of factors that shape the physical context of the museum learning experience. This study makes a theoretical contribution and offers methodological advances to eyetracking research and museum interactive learning experiences. Strategic implications for research and practical recommendations for experience design in a museum are offered.

The relationship between the structure of tourists’ sequence of activities within a destination trip and tourists’ expressed sentiment of those activities is investigated within a moments-based paradigm of experience. A database of approximately 7 million Flickr photos is used to describe the structure of visitor movements within London (e.g. the length of stay of visitors, the volume of visitors to specific London touchpoints, and the sequence in which activity touchpoints are visited) as well as the perceived visitor experience (i.e., positive or negative sentiment) of individual London touchpoints. Results provide theoretical support for the moments-based experience paradigm, and suggest that trip characteristics and trip sequencing can influence value in terms of visitor satisfaction. Methods and findings also demonstrate big data applications that inform the optimal design and management of tourist experiences.

“Last-minute” deals in travel and tourism services are very appealing not only to travellers but also for service providers. Timing and pricing are central to an optimization strategy for last-minute deals for both sides. This study analyses last-minute timing behaviour for self-catering customers and proposes to the supplier an estimation of the critical Last-Minute Momentum (LMM) that is, the optimal moment for launching these kinds of deals. The data emanates from the largest booking of self-catering accommodation platform in the Romand Valais in Switzerland, containing more than 154,000 transactions. The results show that last minute behaviours depend not only on the origin country and season (as previously postulated) but also on the length of the stay, the composition of the party and the destination. For practitioners, the results shed some light on the timing optimization of last-minute campaigns. For scholars, the results demonstrate that last-minute behavior challenges traditional paradigms of the Planning Vacation Process (PVP).

Digital data sources can be useful in measuring the evolution of tourism. In particular, card transactions are a good way of analysing domestic tourism. To do so, firstly, transactions have to be classified as touristic or non-touristic. This paper presents a methodology to identify the usual environment of cardholders, so as to determine whether their transactions are carried out inside or outside that area. The United Nations World Tourism Organization definition of ‘usual environment’ is used as a basis to create the methodology. The resulting procedure can be adapted to different geographies by varying a single parameter. Some tests validating the methodology are shown at the end of this paper.

The wealth of electronically generated communication combined with increased computing power and sophisticated algorithms provides the opportunity for destination managers to listen to travellers. Identification of sentiment with a domain-oriented lexicon is beneficial for natural language processing to analyse public opinion. Indeed, in the context of travel, sentiment analysis enables tourism decision makers to devise marketing and development strategies that address the information learned. This study presents a lexical dictionary approach for sentiment extraction and opinion mining of travel related messages posted using the Twitter microblogging service. In this study, we propose a human coded sentiment dictionary specific to the travel context. Terms were identified from a pool of more than 1.38 million travel related tweets collected over a nine-month period. Human coders assigned sentiment scores to these terms and the travelMT 1.0 dictionary was produced to enhance the existing labMT 1.0 dictionary. The quality of the travelMT 1.0 dictionary was tested against the original labMT 1.0 dictionary and human judges. We found that, with a larger number of travel terms in a tweet, the enhanced dictionary, travelMT 1.0, produces a more accurate sentiment score than the labMT 1.0 dictionary.