CrisisNLP — 2015_Cyclone_Pam_en

A Twitter dataset of 601 tweets from 2015_Cyclone_Pam_en, collected by CrisisNLP Research Group for 2015_Cyclone_Pam_en crisis. Each record contains tweet text, humanitarian category label, timestamp, user metadata. Crisis-related tweets from the 2015_Cyclone_Pam_en event. Suitable for crisis informatics, humanitarian response, text classification.

#Crisis informatics#Crisisnlp#Cyclone pam#Humanitarian#Vanuatu

Download withheld (licence: tweet IDs only) BibTeX JSONSimilar datasets

Analytics

9.4
Flesch–Kincaid grade
US school grade level
10.8
Automated readability index
Frequent terms
vanuatucyclonepamcyclonepampacificpeopletcpamislandtropicalnewsstormhithitssouthwindsdozensolwynhopelikenewsafecatcategoryportaustraliahelpmonsternationviladevastatingislandsweather2015deadfearedpowerfulupdates000thinkingthoughtswarningbearsdirectdisasterlatestloveneedsaysvideonathan
Topic clusters

Topic 0

pam
like
bear
thank
join
old
watch
head

Topic 1

island
hit
vanuatu
storm
pacific
nation
devastating
powerful

Topic 2

cyclone
rain
warning
wear
weather
typhoon
cyclonepam
come

Topic 3

pam
cyclone
ocean
leave
pacific
severe
devastation
tropical

Topic 4

pam
cyclone
vanuatu
tropical
hit
category
risk
storm

Topic 5

vanuatu
safe
stay
people
hope
think
warning
good

Topic 6

olwyn
cyclone
coast
continue
cycloneolwyn
worker
cat
coastal

Topic 7

tcpam
update
cyclonepam
vanuatu
alert
late
service
resident

Topic 8

kill
south
fear
dead
pacific
agency
cyclone
death

Topic 9

cyclonepam
vanuatu
stay
thought
bad
safe
think
know
Top hashtags
#cyclonepam130
#vanuatu101
#tcpam40
#pam28
#cyclone20
#news11
#portvila8
#geraldton6
#hmrd6
#auspol5
#disaster5
#cycloneolwyn4
#olwyn4
#rt4
#staysafe4
#tcolwyn4
#terry4
#australia3
#boldandbeautiful3
#climate3

Computed over the full corpus.

Record

Catalog key
crisisnlp-2015_Cyclone_Pam_en
Authors
Imran, Muhammad; Mitra, Prasenjit; Castillo, Carlos
Year
2016
Source paper
Twitter as a Lifeline: Human-annotated Twitter Corpora for NLP of Crisis-related Messages
DOI / arXiv
10.48550/arXiv.1605.05894
License
See source page for citation/usage terms (CrisisNLP dataset)
Records
601
Text corpus
tweet text
Languages
en
Collected
2015 (2010s)
Region
Global (inferred: the platform is used worldwide)

Provenance

Originally published at
https://github.com/ChenBeici/SocialED_datasets/tree/main/raw_data/CrisisNLP link checked

How to cite

BibTeX

@misc{echo2026,
  title  = {ECHO: Exploratory Compendium of Humanity Online},
  author = {Switzer, Braden and Zafarani, Reza},
  year   = {2026},
  url    = {https://echo.directory},
  note   = {Syracuse University}
}

@misc{https://doi.org/10.48550/arxiv.1605.05894,
  doi       = {10.48550/ARXIV.1605.05894},
  url       = {https://arxiv.org/abs/1605.05894},
  author    = {Imran, Muhammad and Mitra, Prasenjit and Castillo, Carlos},
  keywords  = {Computation and Language (cs.CL), Computers and Society (cs.CY), Social and Information Networks (cs.SI), FOS: Computer and information sciences, FOS: Computer and information sciences},
  title     = {Twitter as a Lifeline: Human-annotated Twitter Corpora for NLP of Crisis-related Messages},
  publisher = {arXiv},
  year      = {2016},
  copyright = {arXiv.org perpetual, non-exclusive license}
}

APA

Switzer, B., & Zafarani, R. (2026). ECHO: Exploratory Compendium of Humanity Online [Data repository]. Syracuse University. https://echo.directory

Imran, M., Mitra, P., & Castillo, C. (2016). CrisisNLP — 2015_Cyclone_Pam_en [Data set]. https://doi.org/10.48550/arXiv.1605.05894

MLA

Switzer, Braden, and Reza Zafarani. ECHO: Exploratory Compendium of Humanity Online. Syracuse University, 2026, echo.directory.

Imran, Muhammad, et al. CrisisNLP — 2015_Cyclone_Pam_en. 2016, doi.org/10.48550/arXiv.1605.05894.

BibTeX · RIS · CSL-JSON

Similar datasets 10 all with scores →