A Threefold Similarity Analysis of Crowdsourcing Feeds

Crowdsourcing is a valuable social sensing for the smarter city. We present an approach for classifying crowd sourced feeds from a threefold point of view, namely image, text, and geography. The main idea is to extract feeds within a specific geographic range, and then analyze similarity of image color and text semantic. The approach enables to identify feeds that report the same issue, hence filtering redundant information. Based on proved methods and algorithms, such approach has been implemented in a software application, called CITY FEED, that is used by the Municipality of Pavia.