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.
@article{arxiv.2211.11468,
title = {Enhancing Crisis-Related Tweet Classification with Entity-Masked Language Modeling and Multi-Task Learning},
author = {Philipp Seeberger and Korbinian Riedhammer},
journal= {arXiv preprint arXiv:2211.11468},
year = {2022}
}