Transformer-based Multi-task Learning for Disaster Tweet Categorisation

TL;DR

This paper presents a transformer-based multi-task learning approach for classifying disaster-related tweets by information type and priority, demonstrating state-of-the-art performance and the benefits of ensemble methods in this domain.

Contribution

The paper introduces a novel transformer-based multi-task learning model for disaster tweet classification and shows that ensemble techniques significantly enhance performance.

Findings

Achieves competitive performance on TREC IS track

Ensemble approach improves effectiveness substantially

Sets new state-of-the-art in disaster tweet classification

Abstract

Social media has enabled people to circulate information in a timely fashion, thus motivating people to post messages seeking help during crisis situations. These messages can contribute to the situational awareness of emergency responders, who have a need for them to be categorised according to information types (i.e. the type of aid services the messages are requesting). We introduce a transformer-based multi-task learning (MTL) technique for classifying information types and estimating the priority of these messages. We evaluate the effectiveness of our approach with a variety of metrics by submitting runs to the TREC Incident Streams (IS) track: a research initiative specifically designed for disaster tweet classification and prioritisation. The results demonstrate that our approach achieves competitive performance in most metrics as compared to other participating runs. Subsequently, we find that an ensemble approach combining disparate transformer encoders within our approach helps to improve the overall effectiveness to a significant extent, achieving state-of-the-art performance in almost every metric. We make the code publicly available so that our work can be reproduced and used as a baseline for the community for future work in this domain.