Few-shot tweet detection in emerging disaster events

TL;DR

This paper explores few-shot learning methods for detecting relevant tweets during emerging disaster events, aiming to enable rapid, event-specific message filtering with minimal data collection.

Contribution

It compares matching networks, prototypical networks, and a modified one-class prototypical approach for disaster tweet detection in a few-shot setting.

Findings

Few-shot models effectively identify relevant disaster tweets with limited data

Modified one-class prototypical model improves detection in one-class scenarios

Few-shot approaches outperform traditional universal models in emerging crises

Abstract

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.