Less After-the-Fact: Investigative visual analysis of events from streaming twitter

Abstract

News and events are traditionally broadcasted in an “After-the-Fact” manner, where the masses react to news formulated by a group of professionals. However, the deluge of information and real-time online social media sites have significantly changed this information input-output cycle, allowing the masses to report real-time events around the world. Specifically, the use of Twitter has resulted in the creation of a digital wealth of knowledge that directly associates to such events. Although governments and industries acknowledge the value of extracting events from the TwitterSphere, unfortunately the sheer velocity and volume of tweets poses significant challenges to the desired event analysis. In this paper, we present our Geo and Temporal Association Creator (GTAC) which extracts structured representations of events from the Twitter stream. GTAC further supports event-level investigative analysis of social media data through interactively visualizing the event indicators (who, when, where, and what). Using GTAC, we are trying to create a near real-time analysis environment for analysts to identify event structures, geographical distributions, and key indicators of emerging events.