Information Technology & Tourism最新文献

This study analyzes how review length relates to numerical scores on online platforms, conducting separate analyses for positive and negative comments and accounting for non-linearities in the relationship. Moreover, we consider the role played by blank reviews, i.e. those ratings without textual content, a topic that has been largely overlooked in previous works. Our findings suggest that blank reviews are positively correlated with higher scores, which has important implications for the ordering of reviews on online platforms. We propose that these results can be explained by social exchange theory, which suggests that less strict review policies could increase engagement and lead to a more balanced evaluation of establishments. This could offset the tendency of dissatisfied guests to disproportionately report negative experiences. Future studies should compare the composition of guest reviews on platforms adopting differing review policies.

With the advancement of AI-powered technologies, machine translation (MT) has had a notable influence on tourists’ travel experiences by altering the way they use or understand language in destinations. The purpose of this study is to identify and describe travelers’ viewpoints of MT derived from their experience based on consumption value theory (CVT). This paper also utilized Q methodology to gain insights into travelers’ perspectives on MT by performing Q-sorting on 32 South Koreans who used MT while traveling abroad. The analysis of using Ken-Q revealed three major perspectives: a linguistic shortcut, the compass of comprehensibility, and the pocket assistant of linguistic abundance, in which conditional, functional, epistemic, and social values are reflected. The findings generate both theoretical and practical implications for enhancing the utilization of MT and its significance in tourism-related activities.

The Tourist Trip Design Problem (TTDP) is a challenging task that involves designing an optimal travel itinerary for a tourist visiting multiple Points of Interest (POIs) within a specific city or region, while considering budget, time constraints, and multiple knapsack constraints. To create a customized itinerary that maximizes enjoyment and minimizes travel costs, factors such as POI distance, attractions, categories of POIs, and the tourist’s preferences must be considered. This paper introduces a local search technique for an extended variant of TTDP that includes pattern sequence for POI categories, recently defined by our team. Our approach builds upon existing state-of-the-art solvers based on ILS for the Multi Constrained Team Orienteering Problem with Time Windows (MCTOPTW) variant. The approach has been put to the test and proved its worth by generating high-quality solutions, comparable to the state-of-the-art solvers for simpler variants of TTDP. A test set of 146 instances was used to demonstrate the approach’s effectiveness.

Social media platforms like Instagram significantly influence tourists’ travel decisions by providing them with valuable insights, recommendations, authentic information, and points of interest. However, photos shared with location-specific hashtags, even those related to tourist attractions, do not always reflect the actual destination, creating challenges for potential visitors seeking accurate information. To assist tourists in finding pertinent tourism information for specific destinations, we propose VISTA: Visual Identification of Significant Travel Attractions. The proposed method employs deep learning and active learning techniques to automatically classify photos into: ‘Tourism-Related’ photos (i.e., photos related to tourism) and ‘Non-Tourism-Related’ photos (i.e., photos unrelated to tourism). To train our machine learning classifier, we created a dataset containing photos of the 10 most popular Israeli cities on Instagram. The classifier obtained an accuracy score of 0.965 and a weighted F1 score of 0.964. Evaluating our classifier’s global generalization on the InstaCities100K dataset, derived from InstaCities1M, yielded an accuracy score of 0.958 and a weighted F1 score of 0.959. The effectiveness of VISTA was demonstrated by comparing tourism-related and non-tourism-related photos in terms of photo proportion, user engagement, and object comparison. We found that most photos published on Instagram associated with cities are irrelevant to tourists and that tourism-related photos received more likes than non-tourism-related photos. Finally, there was a low overlap between objects in the two photo collections. Based on these results, we conclude that VISTA can help tourists tackle the problem of finding relevant tourism-related photos among the high volume of photos available on Instagram.

In the hotel booking market, high click-through rates are essential for online travel agencies (OTAs) to earn commissions. Given the dominance of mobile devices in web traffic, analyzing the mobile click-through decision-making process plays a vital role in search engine optimization. This study proposes a sequential framework that leverages Bayesian inference to model individual users’ click-through behaviors using user digital footprints, which encompass sequences of search, browse, compare, and click-through actions. This framework extracts three categories of information based on the degrees of dynamism in the hotel search process, ranging from less dynamic to highly dynamic levels: static hotel attributes, information cues in the search results, and temporal characteristics of user behaviors. Extensive experiments on a global OTA mobile clickstream dataset with over 600,000 observations reveal the substantial superiority of the proposed framework over the baseline models like probit regression and Naive Bayes. Notably, temporal characteristics emerge as the most important category. Drawing on our model, we delve into the interpretability of these three information categories. Additionally, we compare their varying impacts across different devices. Beyond these findings, this study offers valuable managerial implications for mobile OTA search engine marketing and optimization.

Technology has rendered as a means to reshape tourist experience, but it may backfire to created unintended consequences when technological devices are overused to dominate the experience creation process. This study investigates how and why smart technologies fail to reach their intended goals, and the unfavorable consequences in such circumstances from the tourist perspective. The present inquiry utilized a qualitative field research through observations and semi-structured interviews based on data collected in two smart museums that put technology in center stage. The results present a phenomenon we coined as peril of smart technology, identifying three major categories of this phenomenon: emotional disresonance, technology-induced cognitive dissonance, and technology loathing. This study contributes to the literature by illuminating the dark side of smart technology in the museum context, which sets it apart from the extant literature that focuses primarily on the positive side of technology. Additionally, the findings provide practical implications for museum operators.

The measurement of destination image from visual media such as online photography is of growing significance to destination managers and marketers who want to make better decisions and attract more visitors to their destination. However, there is no single approach with proven accuracy for doing this. We present a new approach where we fine-tune a deep learning model for a predetermined set of cognitive attributes of destination image. We then train state of the art neural networks using labelled tourist photography and test accuracy by comparing results with a ground truth dataset built for the same set of visual classes. Comparing our fine-tuned model against results which follow past approaches, we demonstrate that the pre-trained models without fine-tuning are not as accurate in capturing all of the destination image’s cognitive attributes. This is, to the best of our knowledge, the first deep learning computer vision model trained specifically to measure the cognitive component of destination image from photography and can act as a benchmark for future systems.

After the temporary shock of the Covid-19 pandemic, the rapid recovery and resumed growth of the tourism sectors accelerates unsustainable tourism, resulting in local (over-)crowding, environmental damage, increased emissions, and diminished tourism acceptance. Addressing these challenges requires an active visitor management system at points of interest (POI), which requires local and timely POI-specific occupancy predictions to predict and mitigate crowding. Therefore, we present a new approach to measure visitor movement at an open-spaced, and freely accessible POI and evaluate the prediction performance of multiple occupancy and visitor count machine learning prediction models. We analyze multiple case combinations regarding spatial granularity, time granularity, and prediction time horizons. With an analysis of the SHAP values we determine the influence of the most important features on the prediction and extract transferable knowledge for similar regions lacking visitor movement data. The results underline that POI-specific prediction is achievable with a moderate relation for occupancy prediction and a strong relation for visitor count prediction. Across all cases, XGBoost and Random Forest outperform other models, with prediction accuracy increasing as the prediction time horizon shortens. For effective active visitor management, combining multiple models with different spatial aggregations and prediction time horizons provides the best information basis to identify appropriate steering measures. This innovative application of digital technologies facilitates information exchange between destination management organizations and tourists, promoting sustainable destination development and enhancing tourism experience.

Virtual reality has emerged as a powerful tool for the design of immersive tourism experiences. Prior studies have primarily relied on externally produced 360-degree stimuli, with the potential to undermine causal inference among concepts and increase risk of flattening real-world responses. Consequently, building on design principles embedded in human–computer interaction, this paper draws on an exemplar of an iconic nature-based tourism destination to elucidate the process which underpins the development of 360-degree stimuli, with an emphasis on the manipulation of ‘presence’. Emergent findings demonstrate the efficacy of a five-step procedure: (1) concept manipulation and location selection; (2) preliminary field filming; (3) expert evaluation and preliminary test; (4) re-filming and editing; and (5) confirmatory test. Physiological and self-report measures assessed the internal and external validity of the 360-degree stimuli, confirming the effectiveness of the manipulation. This research contributes to knowledge through the transfer of core principles from information technology and tourism into the design of immersive 360-degree stimuli to facilitate rigorous manipulation and multi-measurement in experimental design in tourism. Future research should focus on enhancing validity and reliability of internally produced immersive stimuli, overcoming methodological challenges with the design and manipulation of stimuli in tourism research.

Peer-to-peer accommodation has generated an ecosystem of platforms with different business models (i.e., for-profit and nonprofit). This study aims to identify and compare attributes that influence guests’ experiences as reviewed on the for-profit platform Airbnb and the nonprofit platforms Couchsurfing.com and HomeExchange.com according to a three-dimensional experience theoretical model and a methodological approach to interpret these attributes. The study used text-mining techniques to analyze 772,768 online travel reviews representing Spain’s four most-visited cities. Findings show that attributes influencing guests’ experiences in the case of nonprofit platforms relate to the authenticity dimension of experience (e.g., existential values and travel philosophy). Furthermore, guests reported that their guest–host interaction was the most representative attribute and that, unlike with Airbnb, such interaction helped to create a more authentic experience. By contrast, attributes of guests’ experiences in the case of for-profit platforms related to the physical amenities and characteristics that guests would expect to find in hotels. Those results can allow destination managers and accommodation practitioners to better understand users of peer-to-peer accommodations and thereby design more suitable strategies and experiences for them.