Investigating Māori language use on Twitter

Code for building and analysing two different Twitter corpora:

The Reo Māori Twitter (RMT) Corpus V2 comprising 94,163 Māori-language tweets (updated 12 November 2022). The first version of the corpus (reported in our paper) contained 79,018 tweets, and is still available for download.
The Māori Loanword Twitter (MLT) Corpus containing 4.5 million tweets of Māori loanwords in New Zealand English (NZE).

Code relating to the Māori-English Twitter (MET) Corpus is hosted on another GitHub repo.

For further information, please visit our companion website.

Name		Name	Last commit message	Last commit date
Latest commit History 323 Commits
docs		docs
hybrid_hashtags		hybrid_hashtags
language_classifier		language_classifier
lib		lib
loanword_networks		loanword_networks
mlt_corpus		mlt_corpus
rmt_corpus		rmt_corpus
.Rhistory		.Rhistory
.gitignore		.gitignore
README.md		README.md
__init__.py		__init__.py
_config.yml		_config.yml
lala.bin		lala.bin
main.py		main.py
mkdocs.yml		mkdocs.yml
nohup.out		nohup.out

Waikato/kiwiwords