3

I have indexed i.e 400 documents. Then i want to give two documents and lucene to return me the similarity between those two documents. Is that possible? Thanks in advance.

Lefteris Bab
  • 787
  • 9
  • 19

1 Answers1

0

In brief. calculate the cosine of two document vector.

example code

pensz
  • 1,871
  • 1
  • 13
  • 18
  • Yes, but if someone wants a good similarity measure, I think that he needs a good stemmer and to remove stopwords too. Is there an easy way to do this? Except Lucene? – Lefteris Bab Nov 25 '12 at 14:23