Stemming and further text cleaning for the LDA model

ayman-mezghani / Wikipedia-Graph-Processor

bachelor's semester project

0 stars 0 forks source link

Stemming and further text cleaning for the LDA model #4

Closed ayman-mezghani closed 4 years ago

ayman-mezghani commented 4 years ago

It's all in the title

ayman-mezghani commented 4 years ago

I used a lemmatizer (WordNet) from nltk. The results are slightly better. I will experiment with a stemmer. I will also try to stack them and see what I get.