Travel Information Research Articles

P-1881. Don't Know Much About Geography? Decision Support for Frontline Clinicians Evaluating Patients with Suspected High Consequence Infectious Diseases

Abstract Background High Consequence Infectious Diseases (HCIDs) are acute infectious diseases characterized by high case-fatality rates, few (if any) rapidly accessible treatments, and person-to-person spread in the absence of appropriate transmission-based precautions. Rapid identification and isolation of suspected cases is critical, however, diagnosis is challenging because HCIDs can manifest with nonspecific symptoms and specialized knowledge about the geography of current outbreaks, as well as HCID-specific exposure risk factors and incubation periods, are not uniformly known to healthcare personnel (HCP) performing patient evaluations. Clinical Decision Support Systems (CDSS) embedded within the electronic health record (EHR) may facilitate assessment.Figure 1:EvalHCID Clinical Decision Support System DemonstrationFrom top to bottom, EvalHCID automatically imports travel information from the routine travel screening conducted during initial patient triage. Additional travel can be manually entered, with an itinerary of up to 4 countries. By cross-referencing a system-wide database of circulating HCIDs, EvalHCID automatically loads an interface to evaluate HCIDs relevant to the patient’s travel history. By subtracting symptom onset date from the last day in country, symptom development outside the relevant incubation period can be identified. Methods We describe the design and development of an EHR-embedded CDSS tool, linked to a travel and symptom screening, and referencing a regularly updated worldwide HCID Watch List, to assist HCP in the evaluation of a returning traveler with infectious symptoms. Performance and user experience of the tool are described.Figure 2:EvalHCID Clinical Decision Support System DemonstrationFrom top to bottom, EvalHCID facilitates collection of epidemiological history that would place a traveler at high risk for the development of an HCID (in this case, the Middle East Respiratory Syndrome). Based on the data entered into EvalHCID, a recommendation regarding risk stratification and next steps is given. Relevant resources are also provided. Results The Evaluate for High Consequence Infectious Disease (EvalHCID) CDSS facilitates identification of patients with travel, symptom, and epidemiological risk factors warranting Person Under Investigation (PUI) status for viral hemorrhagic fevers (including Lassa Fever, Crimean-Congo Hemorrhagic Fever, Marburg Virus Disease, and Ebola Virus Disease) as well as Novel Influenza and the Middle East Respiratory Syndrome (Figures 1 and 2). Using integrated, adaptable logic concordant with public health guidance, EvalHCID can be deployed to rapidly identify patients who meet PUI criteria, while allowing patients who do not meet PUI criteria to proceed with an otherwise appropriate clinical evaluation (Figure 3).Figure 3:EvalHCID Clinical Decision Support System LogicBy incorporating travel history, the dates of travel and symptom onset, relevant symptoms, and epidemiological risk factors, EvalHCID assists frontline healthcare personnel in risk-stratifying returning travelers for HCIDs. Conclusion With highly specialized and accessible HCID expertise embedded within the EHR, HCP identification of patients at high risk for HCIDs is augmented, enabling rapid initiation of appropriate isolation when indicated for PUIs. At the same time, through speeding the evaluation of low-risk patients, care can be improved by allowing diagnosis of more likely clinical conditions. Disclosures All Authors: No reported disclosures

Taxi Fare Prediction Using Various Machine Learning Models

The current architecture of ours has been developed with the help of Random Forest, Lasso Regression, XGBoost(Abbr.), and Ridge Regression among other machine literacy techniques. We have predicted fares relatively well considering various factors such as the number of passengers traveling, date, time, pickup and dropoff latitudes, and longitudes, and so on. Each model is trained and estimated with the help of a dataset consisting of past travel information. Two models were randomly selected to reduce overfitting and enhance conceptualization with regularization techniques like Lasso and Ridge Retrogression. Also, Random Forest and XGBoost(Abbr.), known to handle complicated, nonlinear connections, were applied. Finally, based on a detailed comparison of performances of these models through evaluation metrics such as RMSE (Abbr.) and R2 score (Abbr.), the best method was chosen that could predict the fare. A multi-model method like this ensures delicacy and rigidity-an essential source of insight into dynamic pricing and optimization of mobility efficiency within public spaces.

Resolving ambiguity in natural language for enhancement of aspect-based sentiment analysis of hotel reviews.

In the ever-expanding digital landscape, the abundance of user-generated content on consumer platforms such as Booking and TripAdvisor offers a rich source of information for both travellers and hoteliers. Sentiment analysis, a fundamental research task of natural language processing (NLP) is used for mining sentiments and opinions within this vast reservoir of text reviews. A more specific type of sentiment analysis, i.e., aspect-based sentiment analysis (ABSA), is used when processing customer reviews is required. In ABSA, we aim to capture aspect-level sentiments and intricate relationships between various aspects within reviews. This article proposes a novel approach to ABSA by introducing a novel technique of word sense disambiguation (WSD) and integrating it with the Transformer architecture bidirectional encoder representations from Transformers (BERT) and graph convolutional networks (GCNs). The proposed approach resolves the intriguing ambiguities of the words and represents the review data as a complex graph structure, facilitating the modeling of intricate relationships between different aspects. The combination of bidirectional long short-term memory (BiLSTM) and GCN proves effective in capturing inter-dependencies among various aspects, providing a nuanced understanding of customer sentiments. The experiments are conducted on the RABSA dataset (an enhanced and richer hotel review data collection), and results demonstrate that our approach outperforms previous baselines, showcasing the effectiveness of integrating WSD in ABSA. Furthermore, an ablation study confirms the significant contribution of the WSD module to the overall performance. Moreover, we explore different similarity measures and find that cosine similarity yields the best results when identifying the real sense of a word in a given sentence using WordNet. The findings of our work and future work related to our work create lots of interest for people in the tourism and hospitality industry. This research gives another boost to the concept of the potential of NLP techniques in sentiment analysis. It emphasizes that if we combine the potential of NLP techniques along with state-of-the-art machine learning frameworks, we can shape the future of this field.

Exploring road users' awareness and perceptions of advanced traveler information systems (ATIS) in Kumasi, Ghana

Exploring road users' awareness and perceptions of advanced traveler information systems (ATIS) in Kumasi, Ghana

Can I Trust GenAI to Plan My Next Trip? A Multi-Method Approach to Optimizing Media Mix

Although tourists can now book trips directly using generative artificial intelligence (GenAI), it remains unclear whether the real-time travel information it provides is comprehensive and sufficiently trustworthy enough to make booking decisions. The present research addresses this gap by integrating media richness, trust transfer, and the value-based adoption model (VAM) to investigate the impact of varying levels of travel information richness (text-only, text-image, and text-image-audio) on the booking behaviors of tourists using GenAI such as ChatGPT. With data from 578 participants, we tested the proposed structural and configurational models using a multi-analytical approach. Our findings revealed that the three media richness levels yield both analogous and distinctive effects on tourist perceptions regarding benefits, costs, trust formation, and intentions in ChatGPT online travel booking. Specifically, the text-image group demonstrated the strongest links from media richness to trust in ChatGPT, perceived benefit to value, and ultimately value to increased booking intention. Our findings from configurational modeling confirm a significant opportunity to harness the power of AI-empowered platforms for online travel booking.

A Transport Mode Detection Framework Based on Mobile Phone Signaling Data Combined with Bus GPS Data

Transport mode is one of the important travel characteristics for citizens, which is crucial to the planning and management of urban transportation. With the natural advantages of large sample sizes and a wide coverage of people, more and more researchers adopt mobile phone signaling data (MSD) to detect transport modes. However, due to their low positioning accuracy and temporally irregular nature, identifying transport modes with similar spatiotemporal features, such as the bus and car modes, is particularly challenging. We propose a transport detection framework using MSD combined with bus GPS data to distinguish between the car and bus modes. First, a trajectory matching algorithm is proposed to obtain the most probable bus that mobile phone users may take. Then, more features are mined to improve the accuracy of transport mode detection with different classification models. Furthermore, for signaling trajectories identified as the bus mode, more bus travel information is recognized, including the boarding and alighting station and timestamp. Finally, we built a ground truth dataset and compared the recognition accuracies under different features and classification models. The result shows that the transport mode detection accuracies of the proposed framework with the GBDT, XGBoost, and LightGBM algorithms are all higher than 94%.

The Impact of Digital Technologies on Tourists’ Travel Choices and Overall Experience

Digital technologies have revolutionized the tourism industry, offering tourists unprecedented access to information, bookings, and immersive experiences. The paper's main purpose is to investigate the influence of digital technologies on tourists' decision-making processes and travel experiences in Armenia. The data are based on a survey done among 385 respondents. Findings reveal widespread adoption of digital platforms among tourists in Armenia, contributing positively to their travel experiences. Pearson Chi-square testing reveals a significant relationship among some factors. According to the results, 65.7% plan entertainment in the destination by using the Internet to find out about the main attractions in advance. More than 70% get travel information from Facebook and Instagram. People evaluate digital technologies' impact on their travel experience with an average of 4.28 (1-5 (the best) scale). The Customer satisfaction score is 80.4 %. The main problems are connected with fake information, technical issues, differences in online and offline prices, hotel room pictures, etc. The research underscores the importance of continuous advancements in digital infrastructure and services to further enhance Armenia's tourism sector. The results of this study may be useful for marketing strategies. The study reveals some problems that may be useful for tourism companies and state regulation bodies.

Micro-celebrity marketing-induced travels: a psychological ownership perspective

Purpose Despite the growing interest in micro-celebrities in destination marketing, their role in transferring cognitive, emotional and behavioral outcomes to destination psychological ownership (DPO) is underexplored. This study aims to address this void by investigating how the perceived characteristics of micro-celebrities influence travel intentions through interactive engagement, perceived information quality and DPO. It highlights three pathways for fostering DPO. Design/methodology/approach A survey-based design was developed with 302 samples collected and analyzed using partial least squares structural equation modeling and artificial neural network to examine the hypothesized model. Findings Findings reveal that the expertise and attractiveness of micro-celebrities enhance their perceived personal trustworthiness. This perception encourages social media users to view travel information from micro-celebrities as higher quality and to engage more with them, leading to DPO. Consequently, when social media users experience this psychological ownership, they show a stronger intention to travel to the destination, influenced partly by micro-celebrity marketing. Originality/value This study provides a psychological–developmental perspective on micro-celebrity marketing-induced travels. It underscores the importance of fostering micro-celebrity-induced DPO to establish a sustained, mutually beneficial relationship between tourists and destinations.

Clinical and Epidemiological Information Required for Lyme Disease Surveillance in a Low-Incidence State, California 2011-2017.

Background: Between January 1, 2011, and December 31, 2017, over 12,000 case reports of Lyme disease (LD) were submitted to the California Reportable Disease Information Exchange for further investigation. The number of case reports has tripled compared to previous years, emphasizing the need for efficient estimation and classification methods. We evaluated whether estimation procedures can be implemented in a low-incidence state such as California to correctly classify a case of LD, similar to those procedures used in high-incidence states. Objective: The purpose of this study was to identify whether a minimum number of variables was sufficient to reliably classify cases in California and potentially reduce workload while maintaining the ability to track LD trends in California. Methods: To determine the relative value of diagnostic information, we compared five candidate logistic regression models that were used to classify cases based on information that varied in its degree of difficulty for collection. Results: Our results using California's surveillance data showed that automatically reported data were not sufficient, additional information such as, a patient's clinical presentation and travel history were necessary in a low-incidence state to improve the overall sensitivity of the models. Conclusion: This study may help inform public health surveillance efforts by demonstrating that both clinical and travel information are required to accurately classify a case of LD in a low-incidence state.

The impact of tourists’ motivation to avoid duping on travel information seeking and customer engagement : An integrative approach of uses and gratifications theory and temporal perspective theory

The impact of tourists’ motivation to avoid duping on travel information seeking and customer engagement : An integrative approach of uses and gratifications theory and temporal perspective theory

Essential Accessibility Information About Travel Chains for Everyone.

Accessible travel for all passengers is considered a fundamental right in Europe, addressing both physical and digital accessibility needs. Public transportation must cater to a diverse range of passengers with varying physical conditions, cognitive abilities, and cultural backgrounds. The European Sustainable and Smart Mobility Strategy (2020) underscores the necessity of making mobility accessible and affordable for all, including better connectivity for rural and remote regions. This study examines the importance of considering universal design (UD) in public transport, emphasizing the need for inclusive solutions that benefit as many passengers as possible without requiring specialized adaptations. Research material on the effect of UD measures in accessible travel chains was collected during the planning and implementation phases of the travel chain. The usability and content of travel information sources related to accessibility were examined in these phases. The key findings highlight significant travel chain accessibility challenges in both digital and physical aspects. The planning phase findings show that the digital information about infrastructure accessibility was fragmented, creating difficulties for passengers with low digital literacy to identify, book, purchase, and obtain tickets for accessible transport. The implementation phase revealed inadequately designed physical environments, a lack of multi-sensory guidance, and gaps in the provided digital information. Various accessibility challenges in the physical environment and insufficient digital accessibility information prevent a seamless travel experience for persons with disabilities. While the built environment was initially designed using UD principles, maintenance and functionality have deteriorated over time. Providing accurate digital information about the functionality of infrastructure in advance could enable passengers to make more suitable route choices.

Assessing Satellite-Augmented Connected Vehicle Technology for Security Credentials and Traveler Information Delivery

Vehicle-to-Everything (V2X) technology has the capability to enhance road safety by enabling wireless exchange of telematics and spatiotemporal information between connected vehicles (CVs). Effective V2X communication depends on rapid information sharing between Roadside Units (RSUs), in-vehicle On-Board Units (OBUs), and other connected infrastructure. However, there are increasing concerns with RSUs related to installation needs, reliability, and coverage, especially on rural roadways. This study aims to evaluate the benefits of augmenting CV infrastructure with satellite technology in situations where RSU access or coverage is limited while maintaining V2X security protocols and critical information exchange. The study utilizes data from over 400 personal, fleet, and commercial CVs collected during two real-world pilot deployments in the United States, one in an urban environment in Florida and one in a rural environment in Wyoming. The analysis performed shows that the delivery of critical security credential information and traveler information messages (TIMs) to CVs is dependent on a multitude of environmental and operational reliability factors. Overall, information delivery is faster with dense RSU infrastructure as compared to satellites. However, we show that by augmenting RSU infrastructure with satellite technology, the delivery of information is more robust, improving V2X system reliability, security, and overall road safety.

Digital engagement for travel information among car and public transport users in the Netherlands

As the offer of digital services in transport expands, understanding users’ digital engagement and how it developed over time is important to make informed policy decisions. In particular, we lack an understanding of how both PT (public transport) and car users access and engage with digital technologies and perceive them to be necessary to travel. This article aims at bridging this gap, using a 2022 survey of representative samples from both populations in the Netherlands.There is clear evidence of travellers getting more used to digital technologies over time. In 2022, at most 80% of car and PT users relied at least from time to time on their smartphone to look for travel information. As expected, higher digital skills correlate positively with the likelihood of using smartphone-based travel information. It is worth noting that PT users report higher digital skills than car users, while these samples do not differ significantly in terms of age and education levels. As such, low (perceived) digital skills might be a barrier to switching from the car to public transport.Almost 75% of car and PT users think that travelling is more difficult nowadays without a smartphone, demonstrating a radical shift in societal expectations within a decade and a half. Alternatives like public information displays exist and are still used by the majority, but traditional communication channels are not deemed sufficient anymore to travel worry-free. These perceptions can contribute to shaping reality and may put those with a lower digital access at a disadvantage.

Assessing Dengue Virus Importation Risks in Africa: A Climate and Travel-Based Model.

Dengue is a significant global public health concern that poses a threat to Africa. Particularly, African countries are at risk of viral introductions through air travel connectivity with areas of South America and Asia that experience frequent explosive outbreaks. Limited reporting and diagnostic capacity hinder a comprehensive assessment of continent-wide transmission dynamics and deployment of surveillance strategies in Africa. This study aimed to identify African airports at high risk of receiving dengue infected passengers from Asia, Latin America and other African countries with high dengue incidence. The risk of dengue introduction into Africa from countries of high incidence in Africa, Latin America and within Africa was estimated based on origin-destination air travel flows and epidemic activity at origin. We produced a novel proxy for local dengue epidemic activity using a composite index of theoretical climate-driven transmission suitability and population density, which we used, along with travel information in a risk flow model, to estimate importation risk. We find that countries in East Africa face higher estimated risk of importation from Asia and other East African countries, whereas for West African countries, larger risk of importation is estimated from within the region. Some countries with high risk of importation experience low local transmission suitability which likely hampers the chances that importations lead to local transmission and establishment. Conversely, Mauritius, Uganda, Ivory Coast, Senegal, and Kenya are identified as countries susceptible to dengue introductions during periods of persistent transmission suitability. Our work improves data driven allocation of surveillance resources, in regions of Africa that are at high risk of dengue introduction and establishment, including from regional circulation. This will be critical in detecting and managing imported cases and can improve local response to dengue outbreaks. Rockefeller Foundation, National Institute of Health, EDCTP3 and Horizon Europe Research and Innovation, World Bank Group, Medical Research Foundation, Wellcome Trust, Google.org, Oxford Martin School Pandemic Genomics programme, John Fell Fund.

Analisis Kualitas Layanan Sistem Informasi Aplikasi Access KAI sebagai E-Government dengan E-GovQual

This research evaluates the service quality of the Access By KAI application developed by PT. KAI using the E-GovQual method. This application provides various features such as ticket booking, travel information, and additional services. With a survey of users in Malang and analysis using SPSS. The research results show that the Access By KAI application has good quality, but there are several areas that require improvement, such as effectiveness and service.

Influencer Credibility as A Source of Travel Information for Generation Z to Bali

The development of technology is increasingly rapid, so tourism business managers must keep up with existing technological developments. Social media, especially Instagram, is one of the most widely used platforms in the world, especially for Generation Z. However, some respondents use Instagram for information and entertainment and there is a problem that the information obtained is sometimes not in accordance with reality, especially tourist information. This shows that there is still a lack of credible influencer filtering used in disseminating information about a product or place. This study aims to examine the differences in the interests of Generation Z in assessing the credibility of influencers as a source of tourism information to Bali. In the study, the researcher used a quantitative approach with data analysis used, namely the Multivariate of Variance Test (MANOVA). The number of samples used was 110 respondents per type of tourist. The sampling technique is non-probability sampling with a purposive sampling approach. The results of the study revealed that both domestic and foreign tourist groups judged influencers by their attractiveness to create a feeling of trust in the content disseminated. Meanwhile, for the gender group, they have the same perspective in assessing the credibility of an influencer.

Experience-Sharing to Support Inclusive Travel for Blind and Partially Sighted People

This research aimed to understand the challenges blind and partially sighted people experience in tourism and the travel information they need to plan their travel experiences effectively. To this end, we designed a mixed-methods study consisting of semi-structured interviews and co-design workshops, which were conducted to identify the needs of BPS people and the barriers experienced due to a lack of access to such information. The findings provide insights into the information-seeking process and highlight the role of experience sharing in cultivating a sense of agency, contribution, and interdependence. This study also contributes an accessible tourism ecosystem map based on our findings to highlight the different sources of travel information and their potential role in supporting inclusive travel for BPS people. The findings have implications for research and tourism service design and serve as a tool to motivate research on technologies to support inclusive leisure travel for BPS people and to inform the design of inclusive tourism services.

Variable Message Signs in Traffic Management: A Systematic Review of User Behavior and Future Innovations

Effective traffic management is crucial in addressing the growing complexities of urban mobility, and variable message signs (VMSs) play a vital role in delivering real-time information to road users. Despite their widespread application, there is limited comprehensive understanding of how VMS influence user behavior and optimize traffic flow. This systematic literature review aims to address this gap by examining the effectiveness of VMS in shaping user interactions and enhancing traffic management systems. Using the preferred reporting items for systematic reviews and meta-analyses (PRISMA) methodology, a thorough analysis of relevant studies was conducted to identify key factors influencing VMS impact, including message content and characteristics, complementary sources of information, user demographics, VMS location, and users’ reliance on these signs. Additionally, the review explores the implications of displaying non-critical information on VMS and introduces virtual dynamic message signs (VDMSs) as an innovative approach for delivering public traveler information. The study identifies several research gaps, such as the integration of VMS with vehicle-to-everything (V2X) technologies, navigation systems, the need for validation in real-world scenarios, and understanding behavioral responses to non-critical information on VMS. This review highlights the importance of optimizing VMS for improved user engagement and traffic management, providing valuable insights and directions for future research in this evolving field.

What Do Travelers Know about Traveler's Diarrhea? Impact of a Pre-Travel Consultation in the Lisbon Area, Portugal.

Traveler's diarrhea (TD) is one of the most common travel-related health problems, largely interfering with planned activities and potentially contributing to antimicrobial resistance. This study aimed to characterize the knowledge about TD among pre-travel consultation users of one Portuguese travel clinic and determine the impact of the consultation on knowledge levels. Using a quasi-experimental, separate-sample pretest-posttest design, participants were randomly assigned to two groups: control/pre-consultation group (CG) or experimental/post-consultation group (EG). An anonymous self-administered questionnaire was used. A total of 470 participants were analyzed (227 CG; 243 EG). The EG/post-consultation group showed significant improvement in knowledge, with correct answers increasing from 63% to 75% (p < 0.001). However, knowledge gaps persisted: over 50% were unaware of TD's self-limited nature, 30% did not recognize loperamide as a symptom reliever, and 36% believed all travelers should take antibiotics to prevent TD. The educational level and previous travel outside Europe influenced baseline knowledge; previous travel medicine consultations and information on TD improved knowledge in both groups and made it easier to acquire knowledge on the subject. Thus, a pre-travel consultation effectively increased travelers' TD knowledge. However, post-consultation knowledge levels remained suboptimal, indicating the need for targeted interventions to increase travelers' literacy and optimize pre-travel consultations.

Joint intent detection and slot filling with syntactic and semantic features using multichannel CNN-BiLSTM.

Understanding spoken language is crucial for conversational agents, with intent detection and slot filling being the primary tasks in natural language understanding (NLU). Enhancing the NLU tasks can lead to an accurate and efficient virtual assistant thereby reducing the need for human intervention and expanding their applicability in other domains. Traditionally, these tasks have been addressed individually, but recent studies have highlighted their interconnection, suggesting better results when solved together. Recent advances in natural language processing have shown that pretrained word embeddings can enhance text representation and improve the generalization capabilities of models. However, the challenge of poor generalization in joint learning models for intent detection and slot filling remains due to limited annotated datasets. Additionally, traditional models face difficulties in capturing both the semantic and syntactic nuances of language, which are vital for accurate intent detection and slot filling. This study proposes a hybridized text representation method using a multichannel convolutional neural network with three embedding channels: non-contextual embeddings for semantic information, part-of-speech (POS) tag embeddings for syntactic features, and contextual embeddings for deeper contextual understanding. Specifically, we utilized word2vec for non-contextual embeddings, one-hot vectors for POS tags, and bidirectional encoder representations from transformers (BERT) for contextual embeddings. These embeddings are processed through a convolutional layer and a shared bidirectional long short-term memory (BiLSTM) network, followed by two softmax functions for intent detection and slot filling. Experiments on the air travel information system (ATIS) and SNIPS datasets demonstrated that our model significantly outperformed the baseline models, achieving an intent accuracy of 97.90% and slot filling F1-score of 98.86% on the ATIS dataset, and an intent accuracy of 98.88% and slot filling F1-score of 97.07% on the SNIPS dataset. These results highlight the effectiveness of our proposed approach in advancing dialogue systems, and paving the way for more accurate and efficient natural language understanding in real-world applications.