Timely detection of dynamically unfolding crisis events is challenging. Further, determining which information is accurate and whether reports represent disinformation attacks is challenging. Parsing available data and transforming it into complete information that can be presented to end users may also add overhead to crisis response processes. This disclosure describes a system to detect, triage, and respond to a variety of crisis events. System performance may improve over time, e.g., by evaluating prior events and corresponding output from the system using machine learning techniques.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.