-Calculate weight of each term in all term list. -Calculate Idf factor for each term in document under processing as: Idf (i) = N/ni; where (N = no. of documents in repository, ni = No. of document in which term i occurred) -Calculate W (i) = weight*Idf(i) for each term in the list Now we will create (id X term) matrix as -put W of term where there is match in all term list and doc id list -put 0 where there is mismatch in all term list and doc id list