Active Learning for Event Detection in Support of Disaster Analysis Applications

TL;DR

This paper proposes an active learning framework for disaster analysis in social media images, demonstrating that it can achieve performance comparable to manual annotation, thus reducing the need for extensive labeled data.

Contribution

It introduces a novel active learning approach for disaster image analysis and evaluates its effectiveness on a large-scale dataset across multiple disaster types.

Findings

Active learning achieves comparable performance to manual annotation.

Different sampling and disagreement strategies are effective.

Large-scale disaster image dataset is collected and analyzed.

Abstract

Disaster analysis in social media content is one of the interesting research domains having abundance of data. However, there is a lack of labeled data that can be used to train machine learning models for disaster analysis applications. Active learning is one of the possible solutions to such problem. To this aim, in this paper we propose and assess the efficacy of an active learning based framework for disaster analysis using images shared on social media outlets. Specifically, we analyze the performance of different active learning techniques employing several sampling and disagreement strategies. Moreover, we collect a large-scale dataset covering images from eight common types of natural disasters. The experimental results show that the use of active learning techniques for disaster analysis using images results in a performance comparable to that obtained using human annotated images, and could be used in frameworks for disaster analysis in images without tedious job of manual annotation.