Neurosymbolic AI for mining public opinions about wildfires

Wildfires are among the most threatening hazards to life, property, well-being, and the environment. Studying public opinions about wildfires can help monitor the perception of the impacted communities. Nevertheless, wildfire research is relatively limited compared to other climate-related hazards....

Full description

Saved in:
Bibliographic Details
Main Authors: Duong, Cuc, Raghuram, Vethavikashini Chithrra, Lee, Amos, Mao, Rui, Mengaldo, Gianmarco, Cambria, Erik
Other Authors: Interdisciplinary Graduate School (IGS)
Format: Article
Language:English
Published: 2023
Subjects:
Online Access:https://hdl.handle.net/10356/170507
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-170507
record_format dspace
spelling sg-ntu-dr.10356-1705072023-09-19T01:57:46Z Neurosymbolic AI for mining public opinions about wildfires Duong, Cuc Raghuram, Vethavikashini Chithrra Lee, Amos Mao, Rui Mengaldo, Gianmarco Cambria, Erik Interdisciplinary Graduate School (IGS) School of Computer Science and Engineering Nanyang Environment and Water Research Institute Engineering::Computer science and engineering::Computer applications::Administrative data processing Social sciences::Mass media Neurosymbolic AI Sentiment Analysis Emotion Quantification Opinion Mining Wildfires Wildfires are among the most threatening hazards to life, property, well-being, and the environment. Studying public opinions about wildfires can help monitor the perception of the impacted communities. Nevertheless, wildfire research is relatively limited compared to other climate-related hazards. This article presents our data mining work on public opinions about wildfires in Australia from 2014 to 2021. Three key aspects are analyzed: the topic of concern, sentiment polarization, and perceived emotions. We propose a data filtering approach to acquire golden samples to train a supervised model for emotion quantification to achieve the last target. The results show that the new model produces a more accurate emotion estimation than the existing lexicon approach. Through data analysis, we find that people have seen wildfires as one of the impacts of climate change; trends of tweets can reflect the damage of wildfires in real life. Agency for Science, Technology and Research (A*STAR) Ministry of Education (MOE) This research is supported by the Agency for Science, Technology and Research (A*STAR) under its AME Programmatic Funding Scheme (Project #A18A2b0046). We also appreciate the support from MOE Tier 2 Grant 22-5191-A0001-0: ‘Prediction-toMitigation with Digital Twins of the Earth’s Weather’. In addition, Cuc Duong is supported by Nanyang Research Scholarship 2023-09-19T01:56:35Z 2023-09-19T01:56:35Z 2023 Journal Article Duong, C., Raghuram, V. C., Lee, A., Mao, R., Mengaldo, G. & Cambria, E. (2023). Neurosymbolic AI for mining public opinions about wildfires. Cognitive Computation. https://dx.doi.org/10.1007/s12559-023-10195-8 1866-9956 https://hdl.handle.net/10356/170507 10.1007/s12559-023-10195-8 en A18A2b0046 MOE-T2-22-5191-A0001-0 Cognitive Computation © 2023 The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature. All rights reserved.
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Computer science and engineering::Computer applications::Administrative data processing
Social sciences::Mass media
Neurosymbolic AI
Sentiment Analysis
Emotion Quantification
Opinion Mining
Wildfires
spellingShingle Engineering::Computer science and engineering::Computer applications::Administrative data processing
Social sciences::Mass media
Neurosymbolic AI
Sentiment Analysis
Emotion Quantification
Opinion Mining
Wildfires
Duong, Cuc
Raghuram, Vethavikashini Chithrra
Lee, Amos
Mao, Rui
Mengaldo, Gianmarco
Cambria, Erik
Neurosymbolic AI for mining public opinions about wildfires
description Wildfires are among the most threatening hazards to life, property, well-being, and the environment. Studying public opinions about wildfires can help monitor the perception of the impacted communities. Nevertheless, wildfire research is relatively limited compared to other climate-related hazards. This article presents our data mining work on public opinions about wildfires in Australia from 2014 to 2021. Three key aspects are analyzed: the topic of concern, sentiment polarization, and perceived emotions. We propose a data filtering approach to acquire golden samples to train a supervised model for emotion quantification to achieve the last target. The results show that the new model produces a more accurate emotion estimation than the existing lexicon approach. Through data analysis, we find that people have seen wildfires as one of the impacts of climate change; trends of tweets can reflect the damage of wildfires in real life.
author2 Interdisciplinary Graduate School (IGS)
author_facet Interdisciplinary Graduate School (IGS)
Duong, Cuc
Raghuram, Vethavikashini Chithrra
Lee, Amos
Mao, Rui
Mengaldo, Gianmarco
Cambria, Erik
format Article
author Duong, Cuc
Raghuram, Vethavikashini Chithrra
Lee, Amos
Mao, Rui
Mengaldo, Gianmarco
Cambria, Erik
author_sort Duong, Cuc
title Neurosymbolic AI for mining public opinions about wildfires
title_short Neurosymbolic AI for mining public opinions about wildfires
title_full Neurosymbolic AI for mining public opinions about wildfires
title_fullStr Neurosymbolic AI for mining public opinions about wildfires
title_full_unstemmed Neurosymbolic AI for mining public opinions about wildfires
title_sort neurosymbolic ai for mining public opinions about wildfires
publishDate 2023
url https://hdl.handle.net/10356/170507
_version_ 1779156269705199616