Real-Time Crisis Mapping Using Language Distribution

With the increase in GPS-enabled devices, socialmedia sites, such as Twitter, are quickly becoming a primeoutlet for timely geo-spatial data. Such data can be leveragedto aid in emergency response planning and recovery operations. Unfortunately, the information overload poses significantdifficulty to the quick discovery and identification ofemergency situation areas. The system tackles this challengeby providing real-time mapping of influence areas based onautomatic analysis of the flow of discussion using languagedistributions. The workflow is then further enhanced throughthe addition of keyword surprise mapping which projects the general divergence map onto specific task-level keywords for precise and focused response.