skip to main content


Title: Mapping Spatiotemporal Tourist Behaviors and Hotspots Through Location-Based Photo-Sharing Service (Flickr) Data.
Social media services and location-based photo-sharing applications, such as Flickr, Twitter, and Instagram, provide a promising opportunity for studying tourist behaviors and activities. Researchers can use public accessible geo-tagged photos to map and analyze hotspots and tourist activities in various tourist attractions. This research studies geo-tagged Flickr photos collected from the Grand Canyon area within 12 months (2014/12/01–2015/11/30) using kernel density estimate (KDE) mapping, Exif (Exchangeable image file format) data, and dynamic time warping (DTW) methods. Different spatiotemporal movement patterns of tourists and popular points of interests (POIs) in the Grand Canyon area are identified and visualized in GIS maps. The frequency of Flickr’s monthly photos is similar (but not identical) to the actual tourist total numbers in the Grand Canyon. We found that winter tourists in the Grand Canyon explore fewer POIs comparing to summer tourists based on their Flickr data. Tourists using high-end cameras are more active and explore more POIs than tourists using smart phones photos. Weekend tourists are more likely to stay around the lodge area comparing to weekday tourists who have visited more remote areas in the park, such as the north of Pima Point. These tourist activities and spatiotemporal patterns can be used for the improvement of national park facility management, regional tourism, and local transportation plans.  more » « less
Award ID(s):
1634641
NSF-PAR ID:
10065923
Author(s) / Creator(s):
;
Date Published:
Journal Name:
Progress in Location Based Services 2018. LBS 2018. Lecture Notes in Geoinformation and Cartography. Springer, Cham
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. The main objective of Personalized Tour Recommendation (PTR) is to generate a sequence of point-of-interest (POIs) for a particular tourist, according to the user-specific constraints such as duration time, start and end points, the number of attractions planned to visit, and so on. Previous PTR solutions are based on either heuristics for solving the orienteering problem to maximize a global reward with a specified budget or approaches attempting to learn user visiting preferences and transition patterns with the stochastic process or recurrent neural networks. However, existing learning methodologies rely on historical trips to train the model and use the next visited POI as the supervised signal, which may not fully capture the coherence of preferences and thus recommend similar trips to different users, primarily due to the data sparsity problem and long-tailed distribution of POI popularity. This work presents a novel tour recommendation model by distilling knowledge and supervision signals from the trips in a self-supervised manner. We propose Contrastive Trajectory Learning for Tour Recommendation (CTLTR), which utilizes the intrinsic POI dependencies and traveling intent to discover extra knowledge and augments the sparse data via pre-training auxiliary self-supervised objectives. CTLTR provides a principled way to characterize the inherent data correlations while tackling the implicit feedback and weak supervision problems by learning robust representations applicable for tour planning. We introduce a hierarchical recurrent encoder-decoder to identify tourists’ intentions and use the contrastive loss to discover subsequence semantics and their sequential patterns through maximizing the mutual information. Additionally, we observe that a data augmentation step as the preliminary of contrastive learning can solve the overfitting issue resulting from data sparsity. We conduct extensive experiments on a range of real-world datasets and demonstrate that our model can significantly improve the recommendation performance over the state-of-the-art baselines in terms of both recommendation accuracy and visiting orders. 
    more » « less
  2. null (Ed.)
    This paper introduces a spatiotemporal analysis framework for estimating hourly changing population distribution patterns in urban areas using geo-tagged tweets (the messages containing users’ geospatial locations), land use data, and dasymetric maps. We collected geo-tagged social media (tweets) within the County of San Diego during one year (2015) by using Twitter’s Streaming Application Programming Interfaces (APIs). A semi-manual Twitter content verification procedure for data cleaning was applied first to separate tweets created by humans from non-human users (bots). The next step was to calculate the number of unique Twitter users every hour within census blocks. The final step was to estimate the actual population by transforming the numbers of unique Twitter users in each census block into estimated population densities with spatial and temporal factors using dasymetric maps. The temporal factor was estimated based on hourly changes of Twitter messages within San Diego County, CA. The spatial factor was estimated by using the dasymetric method with land use maps and 2010 census data. Comparing to census data, our methods can provide better estimated population in airports, shopping malls, sports stadiums, zoo and parks, and business areas during the day time. 
    more » « less
  3. Abstract

    A conundrum of wildlife tourism is balancing wildlife conservation and tourist satisfaction. Mountain gorillas (Gorilla beringei)are a flagship species for biodiversity and there is worldwide interest in gorilla trekking safaris. This tourism provides substantial revenue to the government and local communities for gorilla protection, but puts them in danger of zoonotic diseases. To minimize disease transmission, health guidelines are in place for visitors whereby they are asked to remain 7 m from the endangered apes and stay in a cohesive group. Unfortunately, tourists often do not follow these rules and consequently their behavior puts gorillas at risk. The pre‐trekking messages presented to tourists in Bwindi Impenetrable National Park, Uganda were changed to determine if the way messages are stated affects visitor adherence to rules. Tourists (n = 389) either received strategic messages that were positively or negatively framed in relation to expectations to follow specific rules to adhere to health guidelines, and tourist behavior was measured, such as the nearest distance they were to gorillas, and their cohesiveness. Using generalized linear mixed models, it was found that framing messages affected tourist behavior. Tourists who received a negatively framed message had a higher adherence to rules than those who received a positive or control message. They were 75% further from the gorillas (7.26 vs. 4.52 m), more cohesive (0.40 vs. 0.81 m to each other), and approached the gorillas less (0.34 vs. 1.32 times) than the control message. These findings demonstrate that communicating in different ways promotes changes in behavior by tourists, which reduces the chances of epizootic respiratory infections being passed to vulnerable animals. Strategic message framing should be widely considered as a cost‐effective mechanism to promote behavior change during ecotourism.

     
    more » « less
  4. null (Ed.)
    Abstract The available spatial data are rapidly growing and also diversifying. One may obtain in large quantities information such as annotated point/place of interest (POIs), check-in comments on those POIs, geo-tagged microblog comments, and demarked regions of interest (ROI). All sources interplay with each other, and together build a more complete picture of the spatial and social dynamics at play in a region. However, building a single fused representation of these data entries has been mainly rudimentary, such as allowing spatial joins. In this paper, we extend the concept of semantic embedding for POIs (points of interests) and devise the first semantic embedding of ROIs, and in particular ones that captures both its spatial and its semantic components. To accomplish this, we develop a multipart network model capturing the relationships between the diverse components, and through random-walk-based approaches, use this to embed the ROIs. We demonstrate the effectiveness of this embedding at simultaneously capturing both the spatial and semantic relationships between ROIs through extensive experiments. Applications like popularity region prediction demonstrate the benefit of using ROI embedding as features in comparison with baselines. 
    more » « less
  5. During the COVID-19 pandemic, tourism slowed down as the world went into lockdown. This pause in tourism provides a unique opportunity to analyze the environmental and socioeconomic effects of tourism by comparing tourism participation levels before, during, and after the pandemic restrictions. We examined tourism in Iceland, an island nation in the Arctic where international tourists vastly outnumber residents. Specifically, we systematically analyzed the materials, energy, tourist, and information flows, as well as the causes, effects, and agents of tourism in Iceland using the framework of telecoupling (human-nature interactions over distances). Results show that the U.S., U.K., and Nordic countries sent the highest numbers of tourists to Iceland. Flows of tourists to Iceland were tracked based on international flights and cruise ships, with Iceland’s tourism industry returning close to pre-pandemic levels in 2022 for air arrivals, while cruise ship tourism was slower in returning to pre-pandemic levels. Agents in the Icelandic tourism industry include government entities, local businesses, tour operators, and many others. There are diverse causes for tourism in Iceland, such as the demand for nature-based tourism and a cooler climate. International tourism in Iceland had both substantial environmental effects (CO2 emissions, damage to sensitive areas, etc.) and socioeconomic effects (e.g., increases in GDP and jobs). Many effects also spillover to the rest of the world as increases in CO2 emissions contribute to global climate change. Tourism is also expected to continue increasing after Iceland’s 2022 marketing launch of “Iceland Together in Progress.” Since Iceland has had such a strong tourism rebound, other countries around the world (especially other Arctic countries) that are looking to increase their tourism can gain insights from Iceland. However, it is important to make tourism more sustainable (e.g., reduction in CO2 emissions). 
    more » « less