Summarizing tourist destinations by mining user-generated travelogues and photos

Automatically summarizing tourist destinations with both textual and visual descriptions is highly desired for online services such as travel planning, to facilitate users to understand the local characteristics of tourist destinations. Travelers are contributing a great deal of user-generated travelogues and photos on the Web, which contain abundant travel-related information and cover various aspects (e.g., landmarks, styles, activities) of most locations in the world. To leverage the collective knowledge of travelers for destination summarization, in this paper we propose a framework which discovers location-representative tags from travelogues and then select relevant and representative photos to visualize these tags. The learnt tags and selected photos are finally organized appropriately to provide an informative summary which describes a given destination both textually and visually. Experimental results based on a large collection of travelogues and photos show promising results on destination summarization.