Content effect

An individual unconsciously stresses particular topics all the time.

An individual is clearly recognized on the basis of 1,500 rarely used words.

Identification of an individual based on the whole of her or his vocabulary /values above the 0.0 level on y-axis/ and on low-frequency words /below the 0.0 level on y-axis); having more than 1,500 words from the author makes the identification precise; the graph by Vladimír Matlach).

See: Faltýnek, D. – Matlach, V.: Hapax remains: Regularity of low-frequency words in authorial texts. Digital Scholarship in the Humanities, Volume 37, Issue 3, September 2022, Pages 693–715. Link
Other references


We are a tech startup. We aim at mining an individual’s digital communication fingerprint to apply in the fields of state security, online psychotherapy, self-development, HR and marketing.

OLOMOUC 779 00
IČO 17378885

Contact US


Copyright © 2023