Analysis of Social Media Data using Multimodal Deep Learning for Disaster Response

TL;DR

This paper introduces a multimodal deep learning approach combining text and image data from social media to improve disaster response analysis, outperforming single-modality models.

Contribution

It presents a novel multimodal deep learning architecture that jointly learns from text and image data for disaster response, which was not extensively explored before.

Findings

Multimodal model outperforms single-modality models in disaster data analysis.

Deep learning architecture effectively combines text and image features.

Experimental results on real-world datasets validate the approach.

Abstract

Multimedia content in social media platforms provides significant information during disaster events. The types of information shared include reports of injured or deceased people, infrastructure damage, and missing or found people, among others. Although many studies have shown the usefulness of both text and image content for disaster response purposes, the research has been mostly focused on analyzing only the text modality in the past. In this paper, we propose to use both text and image modalities of social media data to learn a joint representation using state-of-the-art deep learning techniques. Specifically, we utilize convolutional neural networks to define a multimodal deep learning architecture with a modality-agnostic shared representation. Extensive experiments on real-world disaster datasets show that the proposed multimodal architecture yields better performance than models trained using a single modality (e.g., either text or image).