Abstract
“A picture is worth a thousand words”. Analysis of the visual content of tourist photos is an effective way to explore the image of tourist destinations. With the development of computer deep learning and big data mining technology, identifying the content of massive numbers of tourist photos by convolutional neural network (CNN) approaches breaks through the limitations of manual approaches of identifying photos’ visual information, e.g., small sample size, complex identification process, and results deviation. In this study, 531,629 travel photos of Jiangxi were identified as 365 scenes through deep learning technology. Through the latent Dirichlet allocation (LDA) model, five major tourism topics are found and visualized by map. Then, we explored the spatial and temporal distribution characteristics of different tourism scenes based on hot spot analysis technology and the seasonal evaluation index. Our research shows that the visual content mining on travel photos makes it possible to understand the tourism destination image and to reveal the temporal and spatial heterogeneity of the image, thereby providing an important reference for tourism marketing.
Highlights
Tourism destination image (TDI) refers to the collection of people’s ideas, thoughts, and impressions of a tourist destination, which plays an important role in the process of tourists choosing a destination, as well as the selection of the appropriate destination marketing strategies [1,2]
We introduce the main tourism scenes and the main tourism latent Dirichlet allocation (LDA) topics composed of tourism scenes in Jiangxi
We proposed a data-driven framework for tourism destination image characterization with the support of user-generated content (UGC) photographs data
Summary
Tourism destination image (TDI) refers to the collection of people’s ideas, thoughts, and impressions of a tourist destination, which plays an important role in the process of tourists choosing a destination, as well as the selection of the appropriate destination marketing strategies [1,2]. Traditional TDI research tends to rely on questionnaires or interviews to collect data from tourists or volunteers for TDI measurement [1], which are laborious, costly, and time consuming. These methods can be applied to the study of a tourism image on a small spatial scale. The tourism image of a destination is usually affected by the spatial distribution of tourism resources [4], and the scenery usually changes seasonally [5] It is more challenging, yet meaningful, to develop the research framework of the spatial and temporal distribution of the tourism image. It is of great significance for researchers, tourism managers, and destination marketing organizations (DMO) to understand how tourists perceive scenic spots on a regional scale at different places
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
