The Tourism Analytics Group study social media content, map and analyze customer locations, and recognize patterns in data to answer business, social, and policy-related questions. The Group have worked on projects from the Army Corps of Engineers, Florida Department of Transportation, and the UF Historic St. Augustine organization. The Tourism Analytics Group closely collaborate with international researchers from all over the world.
What we Do
Study social media content, map and analyze customer locations, and recognize patterns in data to answer business, social, and policy-related questions.
Work on the projects from the Army Corps of Engineers, Florida Department of Transportation, and the UF Historic St. Augustine organization.
Closely collaborate with international researchers.
Featured ACADEMIC Articles
Network approach to tourist segmentation via user generated content
Online reviews of destination attractions are considered as a proxy for visitation data reflective of tourists’ interests. The connectivity between attractions is represented with a network of links created by tourists visiting and reviewing multiple attractions. Attraction clusters are revealed by segmenting this network using network analysis tools.
Online public response to a service failure incident: Implications for crisis communications
The study examines the online public response to a high visibility incident of service failure from the crisis communication and image restoration perspectives. A specific incident in a hotel of a popular chain in Beijing, China, which was widely publicized on Chinese social network Weibo, is used as an example. Applying data mining and GIS to the collected data, the study analyzes temporal, spatial, topical, and gender dynamics of public discussions to investigate the usefulness of such data for hospitality providers in crisis. The study finds evidence that the effect of the incident on the general public is moderated by spatial and personal proximity of Weibo users. The discussion topics reflect the nature of the crisis and are affected by communications from the service provider and third parties. Implications for providers of tourism and hospitality services in a crisis of high visibility are discussed.
The sharing economy: a geographically weighted regression approach to examine crime and the shared lodging sector
The sharing economy has gained great market share within the lodging sector by offering cost-effective accommodation solutions. However, it is also troubled by increasing criminal incidents. This study examined the global relationship between the density of Airbnb and crimes in Florida, explored how the relationships vary at the county level. The results suggested that crime-lodging associations vary by listing types but not crime types. Only the Shared Room type consistently exhibited positive associations with both property and violent crimes, while Private Room and Entire Home exhibited negative associations. Local variations were identified by geographically weighted regression, which could be explained by the local tourism development and ethnic diversity degree. We suggested equal efforts in preventing both property and violent crimes in home sharing business. Also regional differences need to be considered when responding to shared lodging crimes.
GPS-Based mobile exercise application: an alternative tool to assess spatio-temporal patterns of visitors’ activities in a national park
The assessment of spatio-temporal patterns of visitors’ activities in national parks is essential to mitigate impacts to natural resources as well as manage experiences. With the use of a GPS-based mobile exercise application dataset, this study explored the spatio-temporal patterns of visitors’ activities in Seoraksan National Park, South Korea. A total of 1,206 anonymous mobile application users along with their 2,571 activity start points were acquired for January 2015 to December 2015. GIS-based hot spot analyses were employed to analyze the spatial patterns of activity points over time. Results indicated activity hot spots for hours (i.e., dawn, morning, afternoon, and evening) as well as risky points (i.e., falling-rocks, risk of structure collapse, or lightning) during dark hours (night) across seasons. Findings from this study can assist managers to allocate their spatio-temporal park management resources effectively to minimize environmental impacts, and enhance visitor experiences and safety. Furthermore, GPS-based mobile exercise application can be used as an alternative tool to assess spatio-temporal use of visitors in national parks.