Weakly-supervised Fine-grained Event Recognition on Social Media Texts for Disaster Management

TL;DR

This paper introduces a weakly supervised method for fine-grained event recognition on social media texts, enabling rapid classifier development for disaster management with minimal human supervision.

Contribution

It proposes a novel clustering-based data labeling approach and context enrichment techniques to efficiently build high-quality classifiers from noisy social media data.

Findings

Classifiers outperform traditional supervised models with significantly less supervision.

Rapid classifier training achieved within 1-2 hours of human effort.

Effective on hurricane-related social media data, demonstrating practical disaster management utility.

Abstract

People increasingly use social media to report emergencies, seek help or share information during disasters, which makes social networks an important tool for disaster management. To meet these time-critical needs, we present a weakly supervised approach for rapidly building high-quality classifiers that label each individual Twitter message with fine-grained event categories. Most importantly, we propose a novel method to create high-quality labeled data in a timely manner that automatically clusters tweets containing an event keyword and asks a domain expert to disambiguate event word senses and label clusters quickly. In addition, to process extremely noisy and often rather short user-generated messages, we enrich tweet representations using preceding context tweets and reply tweets in building event recognition classifiers. The evaluation on two hurricanes, Harvey and Florence, shows that using only 1-2 person-hours of human supervision, the rapidly trained weakly supervised classifiers outperform supervised classifiers trained using more than ten thousand annotated tweets created in over 50 person-hours.