Smart Profiling of City Areas Based on Web Data

摘要: The paper presents a framework for characterizing and profiling city areas from available data provided by online web services sites. These are points of interest (restaurants, services, hotels, schools, churches, shops, wi-fi access points, etc.) disseminated in the city, local news, traffic information, events, lifestyle human behaviors. allows selecting different sources, preprocessing data, extracting meaningful features, executing clustering algorithm to determine profiles single visualizing results on map. definition is based construction virtual grid squared cells city. We employed metropolitan Milan, Italy. tested cell sizes k-means group similar highlight how belonging same cluster, although located zones actually present characteristics. Such can be utmost importance several entities. By exploiting areas, citizens benefit tailored enterprises define ad hoc marketing strategies, governments supported decision making.