Stopwords in Several Languages

List of stopwords by the spaCy 1 package, useful in text mining, analyzing content of social media posts, tweets, web pages, keywords, etc.

Each list is accessible as part of a dictionary stopwords which is a normal Python dictionary.

Stopword Languages

• Arabic

• Azerbaijani

• Bengali

• Catalan

• Chinese

• Croatian

• Danish

• Dutch

• English

• Finnish

• French

• German

• Greek

• Hebrew

• Hindi

• Hungarian

• Indonesian

• Irish

• Italian

• Japanese

• Kazakh

• Nepali

• Norwegian

• Persian

• Polish

• Portuguese

• Romanian

• Russian

• Sinhala

• Spanish

• Swedish

• Tagalog

• Tamil

• Tatar

• Telugu

• Thai

• Turkish

• Ukrainian

• Urdu

• Vietnamese

You can easily explore the available languages and get (and optionally modify) the stopwords by accessing the dictionary as follows:

Run this code

import advertools as adv
adv.stopwords.keys()

dict_keys(['arabic', 'azerbaijani', 'bengali', 'catalan', 'chinese',
'croatian', 'danish', 'dutch', 'english', 'finnish', 'french',
'german', 'greek', 'hebrew', 'hindi', 'hungarian', 'indonesian',
'irish', 'italian', 'japanese', 'kazakh', 'nepali', 'norwegian',
'persian', 'polish', 'portuguese', 'romanian', 'russian', 'sinhala',
'spanish', 'swedish', 'tagalog', 'tamil', 'tatar', 'telugu', 'thai',
'turkish', 'ukrainian', 'urdu', 'vietnamese'])

You can also access the stopwords of a certain language:

Run this code

print(sorted(adv.stopwords['english'])[:5])

print(sorted(adv.stopwords['german'])[:5])

Footnotes

1

Copyright (C) 2016 ExplosionAI UG (haftungsbeschränkt), 2016 spaCy GmbH, 2015 Matthew Honnibal