Text analysis technologies include text data analysis procedures for problems of automatic classification of business documents, e-mails, analysis of user sentiment, automatic document compression, extraction of information (e.g. entities and keywords), excretion of topics from texts, etc.

The course goes through introductory settings how to apply machine learning procedures to user texts, and how to model a problem from the business domain. The course also goes through the basic ways of text representation (TF-IDF and embedinge) and how to conduct learning and evaluation of machine learning models on texts.