Social Media Behaviour Analysis in Disaster-Response Messages of Floods and Heat Waves via Artificial Intelligence

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 a qualitative analysis via topic inference 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 7 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.

Factors Affecting Flood Disaster Preparedness and Mitigation in Flood-Prone Areas in the Philippines: An Integration of Protection Motivation Theory and Theory of Planned Behavior

“…With the rise of social media in this generation, news outlets also began to utilize this to their advantage. This provided people with much faster news dissemination, which is essential, especially during disasters [20]. Since 80.7% of the respondents are Generation Z (ages 10 to 25 years old), who use social media at least 4 h a day, on average [73], many of the respondents spend most of their time on social media, which includes news regarding natural hazards happening worldwide.…”

“…In the era of the internet, social media is growing rapidly and is considered an important source of additional information that can be used in the analysis of crisis and disaster response [20]. According to Arapostathis [21], a number of studies have explored utilizing social media for effective Disaster Management (DM) over the last ten years.…”

Machine Learning Approach to Classification of Online Users by Exploiting Information Seeking Behavior

“…The website category for URLs extracted from the history files is determined using Website Categorization API 5 , which uses IAB Content Taxonomy 6 . The taxonomy offers a 3-tier category system and is used by various research, e.g., [58] to provide website category lookup service. The three levels of categories are combined into 2 level systems reflecting the categories defined by UIC model features, namely browsing preferences and Sharing on OSN content type.…”