Intro-Cultural-Analytics icon indicating copy to clipboard operation
Intro-Cultural-Analytics copied to clipboard

Add non-English stopwords for multilingual text analysis

Open melaniewalsh opened this issue 3 years ago • 2 comments

We need to add information about how to use non-English stopwords for topic modeling and TF-IDF

melaniewalsh avatar Sep 08 '21 20:09 melaniewalsh

I've used https://github.com/stopwords-iso/stopwords-iso in the past - it's got a bunch of languages in case you need the lists.

igorbrigadir avatar Sep 09 '21 11:09 igorbrigadir

Thank you, @igorbrigadir! Just got around to checking this out, and it looks great. I'm looping in @quinnanya just to make sure she knows about this resource, too

melaniewalsh avatar Sep 11 '21 18:09 melaniewalsh