Text Analysis

relevanz = sum ( g i * G i) = 0 .. 1

                        sum ( g i ) = 1

---

• G 1 = number of terms in text / total number of terms

• G 2 = 1 - sum ( sum f ( minTermDistances )) / C
  "the closer the terms are, the better"

• G 3 = f ( singleTermDistribution )
  "the more the terms are spread over the text, the better"

• G 4 = number of different words / total number of words in text
  spam recognition

start         (C) RRZN, W.Sander-Beuermann