The score shown in the keyword feature is called the keyness score and it is counted by the formula below:
f pm rm focus + N / f pm rm ref + N = keyness score
It basically says “the word is X-times (depending on the score result) more frequent in corpus Y than corpus Z”. The meanings of particular elements in the formula above are following:
- f pm rm focus – normalized (per million) frequency of the word in the corpus Y (focus corpus);
- f pm rm ref – normalized frequency of the word in the corpus Z (reference corpus);
- N – equals to 1 by default, it is possible to change it in the advanced options on the scale in the top-right corner.
related topics: