Few-shot tweet detection in emerging disaster events
This addresses the challenge of timely and cost-effective crisis response for emergency responders and organizations by enabling rapid adaptation to new disaster events without extensive data collection or retraining.
The paper tackles the problem of detecting relevant tweets during emerging disaster events by proposing event-specific few-shot models that can generalize from a small number of manually collected examples, showing that modified one-class prototypical networks perform effectively for this task.
Social media sources can provide crucial information in crisis situations, but discovering relevant messages is not trivial. Methods have so far focused on universal detection models for all kinds of crises or for certain crisis types (e.g. floods). Event-specific models could implement a more focused search area, but collecting data and training new models for a crisis that is already in progress is costly and may take too much time for a prompt response. As a compromise, manually collecting a small amount of example messages is feasible. Few-shot models can generalize to unseen classes with such a small handful of examples, and do not need be trained anew for each event. We compare how few-shot approaches (matching networks and prototypical networks) perform for this task. Since this is essentially a one-class problem, we also demonstrate how a modified one-class version of prototypical models can be used for this application.