0
$\begingroup$

I was starting to learn stemming with nltk and a few words were quite inappropriately stemmed. For example:- very was stemmed to 'veri', important to 'import', once to 'onc', poorly to 'poorli' , etc.

I was just thinking that during data analysis, does it cause any error or these errors can be ignored? Or is there a better option for the same purpose

Improve this question
$\endgroup$

1 Answer 1

Reset to default
0
$\begingroup$

The renown algorithm for stemming is Porter stemming algorithm. Hence, you can use stemmer = nltk.stemmer.PorterStemmer() for the stemming. you can test it using stemmer.stem('poorly').

Moreover, you can see this post for more details.

Improve this answer
$\endgroup$
0

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.