Enhancing Crisis-Related Tweet Classification with Entity-Masked Language Modeling and Multi-Task Learning

TL;DR

This paper introduces a novel approach combining entity-masked language modeling and multi-task learning to improve crisis-related tweet classification, addressing biases and imbalance issues for better generalization.

Contribution

It proposes a new multi-task learning framework with entity-masked language modeling to enhance classification accuracy and cross-event generalization in crisis tweet analysis.

Findings

Up to 10% F1-score improvement on TREC-IS dataset

Entity-masking reduces overfitting to specific events

Enhanced cross-event generalization performance

Abstract

Social media has become an important information source for crisis management and provides quick access to ongoing developments and critical information. However, classification models suffer from event-related biases and highly imbalanced label distributions which still poses a challenging task. To address these challenges, we propose a combination of entity-masked language modeling and hierarchical multi-label classification as a multi-task learning problem. We evaluate our method on tweets from the TREC-IS dataset and show an absolute performance gain w.r.t. F1-score of up to 10% for actionable information types. Moreover, we found that entity-masking reduces the effect of overfitting to in-domain events and enables improvements in cross-event generalization.