Exploring Cognitive Sustainability Concerns in Public Responses to Extreme Weather Events: An NLP Analysis of Twitter Data

Berbère, Rihem and Elkefi, Safa and Bhar Layeb, Safa and Tounsi, Achraf (2023) Exploring Cognitive Sustainability Concerns in Public Responses to Extreme Weather Events: An NLP Analysis of Twitter Data. COGNITIVE SUSTAINABILITY, 2 (4). pp. 42-54. ISSN 2939-5240

Preview

Text CogSust_80.pdf Download (562kB) | Preview

Abstract

The United States has a long history of experiencing extreme weather events. Hurricanes are among the most devastating natural disasters that have significant economic and physical impacts on the country. By applying Natural Language Processing (NLP) to Twitter data for sentiment analysis, emotion detection, and topic modelling, this study provides a more thorough understanding of public response and concerns during five study cases of hurricanes that hit the United States: Harvey, Irma, Maria, Ida, and Ian. The findings on sentiment analysis revealed that 64.75% of the tweets were classified as Negative and 35.25% as Positive. For emotion detection, the predominant emotion was anger, with 39.91%. These results were centred around the main public concerns shown by the topic modelling: hurricane management, donation and support, and disaster impacts. Our future work will focus on understanding people’s responses to extreme weather events through the evolving concept of Cognitive Sustainability.

Actions (login required)

Edit Item