Spatial Semantic Scan: Jointly Detecting Subtle Events and their Spatial Footprint
This work addresses the need for rapid detection of local events in text streams, which is crucial for applications like public health surveillance, though it appears incremental as it builds on existing topic modeling and spatial scan methods.
The paper tackles the problem of detecting emerging, spatially compact events in massive text streams, such as disease outbreaks from emergency department data, by proposing the Spatially Compact Semantic Scan (SCSS) method, which jointly identifies events and their spatial footprints through alternating optimization.
Many methods have been proposed for detecting emerging events in text streams using topic modeling. However, these methods have shortcomings that make them unsuitable for rapid detection of locally emerging events on massive text streams. We describe Spatially Compact Semantic Scan (SCSS) that has been developed specifically to overcome the shortcomings of current methods in detecting new spatially compact events in text streams. SCSS employs alternating optimization between using semantic scan to estimate contrastive foreground topics in documents, and discovering spatial neighborhoods with high occurrence of documents containing the foreground topics. We evaluate our method on Emergency Department chief complaints dataset (ED dataset) to verify the effectiveness of our method in detecting real-world disease outbreaks from free-text ED chief complaint data.