Word2Vec on TF-IDF wordlist

HeikoeWin786

Dear all,

I am exploring one possibility i.e. I want to extract the most frequent nouns from user reviews using TF-IDF (let's say the output is TF_IDF_List), the result will be wordlist.
After that, I want to use Word2Vec to find the similarity of the words in the TF_IDF_List.
Then, using k-means to cluster those similar words.
May I know if anyone can guide me how to achieve that in rapidminer?

Your small input will make a big difference to my learning.

thanks much in advance.

MartinLiebig

Hi,

https://community.rapidminer.com/discussion/52465/synonym-detection-with-word2vec should help you.

BR,

Martin