Behaviour in social media for floods and heat waves in disaster response via Artificial Intelligence

TL;DR

This study employs deep neural networks to analyze social media data related to floods and heat waves in the UK, providing insights into public sentiment, behavioral indicators, and climate interactions during disasters.

Contribution

It introduces a machine learning approach combining sentiment analysis and behavioral indicators with climate data to enhance disaster response insights from social media.

Findings

Positive message rate is around 8% for disaster-related posts.

The approach is transferable to other social media datasets.

Behavioral indicators align with climate variables to inform disaster phases.

Abstract

This paper analyses social media data in multiple disaster-related collections of floods and heat waves in the UK. The proposed method uses machine learning classifiers based on deep bidirectional neural networks trained on benchmark datasets of disaster responses and extreme events. The resulting models are applied to perform sentiment and qualitative analysis of inferred topics in text data. We further analyse a set of behavioural indicators and match them with climate variables via decoding synoptical records to analyse thermal comfort. We highlight the advantages of aligning behavioural indicators along with climate variables to provide with additional valuable information to be considered especially in different phases of a disaster and applicable to extreme weather periods. The positiveness of messages is around 8% for disaster, 1% for disaster and medical response, 7% for disaster and humanitarian related messages. This shows the reliability of such data for our case studies. We show the transferability of this approach to be applied to any social media data collection.