Event-Related Bias Removal for Real-time Disaster Events

TL;DR

This paper introduces an adversarial neural approach to remove event-specific biases from social media data, enhancing real-time classification of actionable crisis-related posts, especially for new, unseen events.

Contribution

We propose a novel adversarial neural model that effectively removes latent event biases, improving the generalizability of disaster-related post classification.

Findings

Improved accuracy in classifying important crisis posts.

Enhanced model generalization to unseen event types.

Reduction of event-specific bias effects.

Abstract

Social media has become an important tool to share information about crisis events such as natural disasters and mass attacks. Detecting actionable posts that contain useful information requires rapid analysis of huge volume of data in real-time. This poses a complex problem due to the large amount of posts that do not contain any actionable information. Furthermore, the classification of information in real-time systems requires training on out-of-domain data, as we do not have any data from a new emerging crisis. Prior work focuses on models pre-trained on similar event types. However, those models capture unnecessary event-specific biases, like the location of the event, which affect the generalizability and performance of the classifiers on new unseen data from an emerging new event. In our work, we train an adversarial neural model to remove latent event-specific biases and improve the performance on tweet importance classification.