Mining Social Media to Identify Heat Waves

Francesca Cecinati, Tom Matthews, Sukumar Natarajan, Nick McCullen, David Coley

Research output: Contribution to journalArticle

Abstract

Heat waves are one of the deadliest of natural hazards and their frequency and intensity will likely increase as the climate continues to warm. A challenge in studying these phenomena is the lack of a universally accepted quantitative definition that captures both temperature anomalies, and associated mortality. We test the hypothesis that social media mining can be used to identify heat wave mortality. Applying the approach to India, we find that the number of heat-related tweets correlates with heat-related mortality, much better than traditional climate-based indicators, especially at larger scales, which identify many heat wave days that do not lead to excess mortality. We conclude that social media based heat wave identification can complement climatic data and can be used to 1) study heat wave impacts at large scales or in developing countries, where mortality data are difficult to obtain and uncertain, and 2) to track dangerous heat wave events in real time.
LanguageEnglish
JournalInternational Journal of Environmental Research and Public Health
Volume16
Issue number5
DOIs
StatusPublished - 2 Mar 2019

Fingerprint

Infrared Rays
Social Media
mortality
heat
Mortality
Climate
Hot Temperature
hazards
climate
Developing Countries
India
Developing countries
Hazards
Temperature
anomalies

Cite this

Mining Social Media to Identify Heat Waves. / Cecinati, Francesca; Matthews, Tom; Natarajan, Sukumar; McCullen, Nick; Coley, David.

In: International Journal of Environmental Research and Public Health, Vol. 16, No. 5, 02.03.2019.

Research output: Contribution to journalArticle

@article{78ae1f16eab446bbb1c861dd000b45ac,
title = "Mining Social Media to Identify Heat Waves",
abstract = "Heat waves are one of the deadliest of natural hazards and their frequency and intensity will likely increase as the climate continues to warm. A challenge in studying these phenomena is the lack of a universally accepted quantitative definition that captures both temperature anomalies, and associated mortality. We test the hypothesis that social media mining can be used to identify heat wave mortality. Applying the approach to India, we find that the number of heat-related tweets correlates with heat-related mortality, much better than traditional climate-based indicators, especially at larger scales, which identify many heat wave days that do not lead to excess mortality. We conclude that social media based heat wave identification can complement climatic data and can be used to 1) study heat wave impacts at large scales or in developing countries, where mortality data are difficult to obtain and uncertain, and 2) to track dangerous heat wave events in real time.",
author = "Francesca Cecinati and Tom Matthews and Sukumar Natarajan and Nick McCullen and David Coley",
year = "2019",
month = "3",
day = "2",
doi = "10.3390/ijerph16050762",
language = "English",
volume = "16",
journal = "International Journal of Environmental Research and Public Health",
issn = "1660-4601",
publisher = "Molecular Diversity Preservation International",
number = "5",

}

TY - JOUR

T1 - Mining Social Media to Identify Heat Waves

AU - Cecinati, Francesca

AU - Matthews, Tom

AU - Natarajan, Sukumar

AU - McCullen, Nick

AU - Coley, David

PY - 2019/3/2

Y1 - 2019/3/2

N2 - Heat waves are one of the deadliest of natural hazards and their frequency and intensity will likely increase as the climate continues to warm. A challenge in studying these phenomena is the lack of a universally accepted quantitative definition that captures both temperature anomalies, and associated mortality. We test the hypothesis that social media mining can be used to identify heat wave mortality. Applying the approach to India, we find that the number of heat-related tweets correlates with heat-related mortality, much better than traditional climate-based indicators, especially at larger scales, which identify many heat wave days that do not lead to excess mortality. We conclude that social media based heat wave identification can complement climatic data and can be used to 1) study heat wave impacts at large scales or in developing countries, where mortality data are difficult to obtain and uncertain, and 2) to track dangerous heat wave events in real time.

AB - Heat waves are one of the deadliest of natural hazards and their frequency and intensity will likely increase as the climate continues to warm. A challenge in studying these phenomena is the lack of a universally accepted quantitative definition that captures both temperature anomalies, and associated mortality. We test the hypothesis that social media mining can be used to identify heat wave mortality. Applying the approach to India, we find that the number of heat-related tweets correlates with heat-related mortality, much better than traditional climate-based indicators, especially at larger scales, which identify many heat wave days that do not lead to excess mortality. We conclude that social media based heat wave identification can complement climatic data and can be used to 1) study heat wave impacts at large scales or in developing countries, where mortality data are difficult to obtain and uncertain, and 2) to track dangerous heat wave events in real time.

U2 - 10.3390/ijerph16050762

DO - 10.3390/ijerph16050762

M3 - Article

VL - 16

JO - International Journal of Environmental Research and Public Health

T2 - International Journal of Environmental Research and Public Health

JF - International Journal of Environmental Research and Public Health

SN - 1660-4601

IS - 5

ER -