The First Story Detection (FSD) task evaluates a TDT system that detects when a story discusses a previously unseen event. The task is an abstraction of a TDT system the alerts a user when a new event occurs. The graphic to the right indicates that there are two annotated topics (events) in the corpus, (the red circles and green diamonds), and each event has a first story.

The task can also be thought of as a glass-box evaluation of a Topic Detection system. Part of a topic dection system's tasks is to decide whether or not each story discusses a new event.

To learn more about technology used to do TDT First Story Detection, or to learn how well these systems perform, there were several system description papers submitted for the 1999 TDT workshop. Also, the TDT Research Links contains pointers to related research.