This article is cited in 7 papers

SPECIAL ISSUE: ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING TECHNOLOGIES

Automating the temperament assessment of online social network users

V. D. Oliseenko^a, A. O. Khlobystova^a, A. A. Korepanova^a, T. V. Tulupyeva<sup>ab

a</sup> Laboratory of Theoretical and Interdisciplinary Problems of Computer Science, St. Petersburg Federal Research Center of the Russian Academy of Sciences
^b Department of State and Municipal Administration, Northwestern Institute of Management RANEPA, St. Petersburg, Russia

Abstract: The paper deals with the problem of automating the prediction of the Eysenck Personality Questionnaire (temperament test) results by numerical characteristics extracted from the accounts of users of a popular Russian-language online social network. The purpose of the work is to automate the evaluation of the expression of personality traits of online social network users by comparing the results of the test and the content posted by the user on his or her account using machine learning methods. The result of the work is the construction of classifiers based on CatBoost and random forest models for predicting the expression of extraversion-introversion and neuroticism. The theoretical value of the result lies in the development of the approach to research design in the field of automating the assessment of human personality traits expression. Practical significance lies in the development of a program module for assessing the expression of human personality traits on online social networks.

Keywords: pen model, temperament, machine learning, prediction of personality traits, online social networks.

UDC: 004.8

Presented: A. L. Semenov
Received: 31.08.2023
Revised: 15.09.2023
Accepted: 15.10.2023

DOI: 10.31857/S2686954323601471

 English version: Doklady Mathematics, 2023, 108:suppl. 2, S368–S373

Bibliographic databases:

•