"Clustering in Text mining"

neelam

Hi All,

I want to classify/cluster words depending upon their similarity of meaning.
Like i want to classify all word with negative meaning(no, not, never) into one cluster.
Please tell me how to proceed ahead.

I have performed the tokenization, filtering, stemming n now want to proceed with clustering.
I am also new to this topic, so plz tell me whether my approach is correct or not.

Thanks and Regards,
neelam

land

Hi,
one would usually apply a weighting schema that draws it's weighting from class information of each single document. Unfortunately I cannot give you a full introduction into this complex field, but we are offering courses on the web for such tasks. See our shop for more details.

Greetings,
  Sebastian