Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Sentiment and Social Signals in the Climate Crisis: A Survey on Analyzing Social Media Responses to Extreme Weather Events

Pouya Shaeri, Yasaman Mohammadpour, Alimohammad Beigi, Ariane Middel

TL;DR

This survey addresses the problem of understanding public sentiment on social media during climate-driven extreme events by providing a comprehensive taxonomy of methods from lexicon-based to large language model–driven approaches. It details data collection, annotation strategies, evaluation metrics, and ethical considerations, foregrounding the 2025 Los Angeles forest fires as a core case study. The authors highlight contributions across methodological taxonomy, real-time data challenges, and the societal implications of climate discourse analytics, offering a roadmap for interdisciplinary, multilingual, and multimodal sentiment analysis in crisis contexts. The work emphasizes practical impact for communication, policy, and emergency response, while calling for responsible handling of misinformation and privacy concerns in high-stakes environments.

Abstract

Extreme weather events driven by climate change, such as wildfires, floods, and heatwaves, prompt significant public reactions on social media platforms. Analyzing the sentiment expressed in these online discussions can offer valuable insights into public perception, inform policy decisions, and enhance emergency responses. Although sentiment analysis has been widely studied in various fields, its specific application to climate-induced events, particularly in real-time, high-impact situations like the 2025 Los Angeles forest fires, remains underexplored. In this survey, we thoroughly examine the methods, datasets, challenges, and ethical considerations related to sentiment analysis of social media content concerning weather and climate change events. We present a detailed taxonomy of approaches, ranging from lexicon-based and machine learning models to the latest strategies driven by large language models (LLMs). Additionally, we discuss data collection and annotation techniques, including weak supervision and real-time event tracking. Finally, we highlight several open problems, such as misinformation detection, multimodal sentiment extraction, and model alignment with human values. Our goal is to guide researchers and practitioners in effectively understanding sentiment during the climate crisis era.

Sentiment and Social Signals in the Climate Crisis: A Survey on Analyzing Social Media Responses to Extreme Weather Events

TL;DR

This survey addresses the problem of understanding public sentiment on social media during climate-driven extreme events by providing a comprehensive taxonomy of methods from lexicon-based to large language model–driven approaches. It details data collection, annotation strategies, evaluation metrics, and ethical considerations, foregrounding the 2025 Los Angeles forest fires as a core case study. The authors highlight contributions across methodological taxonomy, real-time data challenges, and the societal implications of climate discourse analytics, offering a roadmap for interdisciplinary, multilingual, and multimodal sentiment analysis in crisis contexts. The work emphasizes practical impact for communication, policy, and emergency response, while calling for responsible handling of misinformation and privacy concerns in high-stakes environments.

Abstract

Extreme weather events driven by climate change, such as wildfires, floods, and heatwaves, prompt significant public reactions on social media platforms. Analyzing the sentiment expressed in these online discussions can offer valuable insights into public perception, inform policy decisions, and enhance emergency responses. Although sentiment analysis has been widely studied in various fields, its specific application to climate-induced events, particularly in real-time, high-impact situations like the 2025 Los Angeles forest fires, remains underexplored. In this survey, we thoroughly examine the methods, datasets, challenges, and ethical considerations related to sentiment analysis of social media content concerning weather and climate change events. We present a detailed taxonomy of approaches, ranging from lexicon-based and machine learning models to the latest strategies driven by large language models (LLMs). Additionally, we discuss data collection and annotation techniques, including weak supervision and real-time event tracking. Finally, we highlight several open problems, such as misinformation detection, multimodal sentiment extraction, and model alignment with human values. Our goal is to guide researchers and practitioners in effectively understanding sentiment during the climate crisis era.

Paper Structure

This paper contains 23 sections, 1 figure, 2 tables.

Table of Contents

  1. Introduction
  2. Preliminaries
  3. Key Concepts
  4. Modeling Paradigms
  5. Data Collection and Annotation
  6. Sources of Climate-Related Social Media Data
  7. Annotation Techniques for Climate Sentiment
  8. Methodology Taxonomy
  9. Lexicon-Based Methods
  10. Traditional Machine Learning Approaches
  11. Deep Learning Approaches
  12. Transformer-Based Models
  13. LLMs for Sentiment Analysis
  14. Event-Centric Case Studies
  15. LA Forest Fires (2025)
  16. ...and 8 more sections

Figures (1)

  • Figure 1: Overview of the climate sentiment pipeline linking extreme events to social media reactions, analyzed through data, models, and their societal impact. Our survey follows this structure, reviewing existing literature across each stage of the pipeline.