Analysis of formal characteristics of text in the CPACT Research: Enhancing the LIWC linguistic processing for the Czech language

Abstract

The paper deals with the use of quantitative text analysis for the processing of Czech verbal communication within psycholinguistic and psychodiagnostic disciplines and description of the process. It focuses on the application of a computer-assisted linguistic procedures, which aims to classify and quantify formal characteristics (e.g., morphology, semantics etc.) of recorded texts. These systems analyze vast amounts of content data and it also facilitates the comparison of the results with other data, e.g., with information about the communicators, such as their personality characteristics (personality traits, motivation etc.). These methods are employed within the CPACT research (Computational Psycholinguistic Analysis of Czech Text), which is carried out from 2016 at the University of South Bohemia in Ceske Budejovice, Czech Republic (EU), and which aims to enrich the current state of knowledge of the psycholinguistic analysis of texts and using advanced procedures for the Czech language processing. The paper describes relevant aspects of its methodology, the theory and the quantitative analysis specifics.