From microblogs to social images: event analytics for situation assessment

With the rising popularity of microblogging sites like Twitter and Jaiku, we are seeing huge volumes of user generated spatio-temporal-thematic data being created in real time. If combined effectively, this multimedia data can be used to detect events, and understand various 'situations' as they are evolving at different spatio-temporal granularity across the world. In this work, we demonstrate the use of a 'social pixel' based approach to situation assessment. Taking inspiration from traditional image pixels which represent aggregation of photon energies at a location, we consider aggregation of user interest levels at a different geo-locations as 'social pixels'. Combining such pixels spatio-temporally allows for creation of social images and video. We demonstrate how the use of relevant media operators upon such 'images', and use of domain based rules can be used to decide relevant control action decisions to be taken at both, micro and macro levels. The ideas are showcased using a Swine flu monitoring application which uses Twitter data.