Speech characteristics of socionic types of internet commentators via corpus analysis (on the material of the Spanish language)

Abstract

This article is devoted to the description of speech characteristics of Spanish-speaking commentators’ socionic types. The focus is on the speech reactions of commentators to the news about vaccination against covid-19. The aim of the work is to evaluate the effectiveness of using corpus analysis techniques to identify the formal speech characteristics of socionic types of Internet commentators. The relevance of the research work is due to the fact that the problem of automatic attribution of a text according to the criterion of the psychotype of its author remains relevant today among specialists in the field of mathematical and computational linguistics. The novelty of the work lies in the use of corpus tools and formal metrics for the analysis of Spanish-language comments.

In the course of the work, we used such methods as contextual, stylistic, qualitative, quantitative and corpus analysis (Voyant Tools web application). The analysis made it possible to obtain interpretable data on the differences in the values ​​of three formal parameters – average words per sentence, vocabulary density, readability index - in the comments of the representatives of six socionic types found in the research corpus. In addition, specific lexical units and grammatical constructions are defined for each type.

The main research perspective is the development of an automatic tool for detecting socionic personality types in social networks, which will be of practical importance for marketers and sociologists.