Computer Analysis of Characters Speech of the XX Century Based on the Corpus of the Russian Story

The final qualifying work is devoted to the computer analysis of the speech of characters based on the materials of the corpus of the Russian short story of the first third of the XX century. The corpus contains 310 short stories by Russian writers which were written between 1900 and 1930. The purpose of the study is to conduct a comparative analysis of the speech on selected sociological variables, such as gender, age, profession, and to identify the features of the characters speech. The research goal is to create a subcorpus of oral speech of the characters and to create frequency dictionaries, bigrams and descriptive statistics for the oral speech of the characters in the stories and to conduct further comparative analysis of the data obtained for each of the social groups. The study reflects how the speech of different characters in the stories is arranged and how the oral speech of the characters differs depending on the sociological variables studied.