Spatiotemporal social media analytics for abnormal event detection and examination using seasonal-trend decomposition
2012 IEEE Conference on Visual Analytics Science and Technology (VAST)
Figure 1 : Social media analysis system including message plots on a map, abnormality estimation charts and tables for message content and topic exploration. It can be seen, how the Ohio High School Shooing on February 27, 2012 is examined using the system. The selected messages, marked as white dots on the map, show retrieved Tweets that are related to the event. Abstract Recent advances in technology have enabled social media services to support space-time indexed data, and internet users
... all over the world have created a large volume of time-stamped, geo-located data. Such spatiotemporal data has immense value for increasing situational awareness of local events, providing insights for investigations and understanding the extent of incidents, their severity, and consequences, as well as their time-evolving nature. In analyzing social media data, researchers have mainly focused on finding temporal trends according to volume-based importance. Hence, a relatively small volume of relevant messages may easily be obscured by a huge data set indicating normal situations. In this paper, we present a visual analytics approach that provides users with scalable and interactive social media data analysis and visualization including the exploration and examination of abnormal topics and events within various social media data sources, such as Twitter, Flickr and YouTube. In order to find and understand abnormal events, the analyst can first extract major topics from a set of se- lected messages and rank them probabilistically using Latent Dirichlet Allocation. He can then apply seasonal trend decomposition together with traditional control chart methods to find unusual peaks and outliers within topic time series. Our case studies show improved situational awareness by incorporating the anomaly and trend examination techniques into a traditional visual analytics system.