Geotag-based travel route recommendation featuring seasonal and temporal popularity

Abstract

In this paper, a geotag-based travel route recommendation algorithm that considers the seasonal and temporal popularity is presented. Travel routes are extracted from geotags attached to Flickr images. Then, landmarks/routes that become particularly popular at a specific time range in a typical season are extracted. By using the Bayes' theory, the transition probability matrix is efficiently calculated. Experiments were conducted using 21 famous sightseeing cities/places in the world. The results have shown that the recommendation accuracy can be improved by 0.9% - 10.3% on average. The proposed algorithm can also be incoorporated into the state-of-the-art algorithms, having a potential for further recommendation accuracy improvement.