Abstract
Depressive disorders and suicide are one of the leading causes of death in most countries around the world; it is one of the three most common causes of death in a group of young people, but so far, no methods have been developed for diagnosing suicidal tendencies. In this connection, the problem of developing methods for identifying people prone to suicidal behavior is becoming especially topical. One of the directions of such research is the search for typological features of the speech related to depression using the methods of mathematical linguistics, automatic text processing and machine learning. In foreign science, the texts of people that were motivated by depression are studied using methods of automatic text processing, machine learning methods, and models that are constructed to allow to classify whether the text is related to depression or not. It seems obvious that in order to develop methods for identifying people who are prone to depression and suicide, it is necessary to analyze not only suicide notes, but also other texts created by people who have committed suicide.