Generalizing to Unseen Disaster Events: A Causal View
This work addresses generalization challenges for disaster response teams using social media data, but it is incremental as it applies existing causal learning to a specific domain.
The paper tackles the problem of event-related biases in social media disaster monitoring systems that hinder generalization to new events, proposing a causal method that improves F1 scores by up to +1.9% across three classification tasks.
Due to the rapid growth of social media platforms, these tools have become essential for monitoring information during ongoing disaster events. However, extracting valuable insights requires real-time processing of vast amounts of data. A major challenge in existing systems is their exposure to event-related biases, which negatively affects their ability to generalize to emerging events. While recent advancements in debiasing and causal learning offer promising solutions, they remain underexplored in the disaster event domain. In this work, we approach bias mitigation through a causal lens and propose a method to reduce event- and domain-related biases, enhancing generalization to future events. Our approach outperforms multiple baselines by up to +1.9% F1 and significantly improves a PLM-based classifier across three disaster classification tasks.