As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
In the era of big data, social media becomes an essential platform for contemporary people to share and socialize. Every day, tons of traveling photos are uploaded by different tourists from the world, which contain much valuable information. It is of considerable significance to mine and analyze the visual contents of the big pictorial data for obtaining tourists’ perception and providing sufficient pieces of evidence for the development of tourism industry. In this study, 36119 photos shoot in Beijing by overseas tourists on the platform of Flickr were screened out by data mining techniques. We made an early attempt to employ three deep learning models in the field of computer vision to analyze the visual content of the photos, which are scene understanding, semantic segmentation, and emotional recognition, and ResNet, DeepLabo, and WSCNet are the specific structures of the three models. A three-step process was adopted for analysis. Firstly, with the employment of scene understanding model, buildings as the dominated perceived tourism attractions in Beijing were selected out. Secondly, 13797 photos of buildings were further analyzed through the deep learning models of semantic segmentation and emotional recognition. At last, the specific relationship between the types of buildings, semantic elements, and emotional characteristics was revealed. The whole study provides an early empirical attempt for the application of big data in the field of tourism.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.