Discovery of Points of Interest with Different Granularities for Tour Recommendation Using a City Adaptive Clustering Framework

Increasing demand for personalized tours tourists travel in an urban area motivates more attention to points of interest (POI) and tour recommendation services. Recently, the granularity POI has been discussed provide detailed information planning, which supports both inside outside routes that would improve tourists' experience. Such systems require a predefined database with different granularities, but existing discovery methods do not consider well treat all POIs as same scale. On other hand, parameters also need be tuned cities, is trivial process. To this end, we propose city adaptive clustering framework discovering granularities article. Our proposed method takes advantage two algorithms cities due automatic identification suitable datasets. Experiments on real-world social image datasets reveal effectiveness our framework. Finally, discovered levels are successfully applied inner planning.