SEMANTIC VALIDATION OF SOCIAL MEDIA GEOGRAPHIC INFORMATION: A CASE STUDY ON INSTAGRAM DATA FOR EXPO MILANO 2015

Abstract. Social media data, such as Instagram posts, can be associated with spatial positions. This information can be exploited to perform spatial analyses, such as identifying distribution patterns of points representing the positions of social media users during an emergency or while attending a specific event or exhibition. However, the geolocation provided by Social Media Geographic Information (SMGI) needs to be validated, in order for the spatial data to be used in a meaningful way in subsequent spatial analyses or mapping procedures. In this paper, a case study is presented based on Instagram data collected during the first two months of the Expo Milano 2015 exhibition, where the spatial data have been validated by exploiting the semantic component of the posts.