• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Automatic Identification of the Author's Psychotype

Student: Zemliak Viktoriia

Supervisor: Tatyana Vladimirovna Romanova

Faculty: Faculty of Humanities (Nizhny Novgorod)

Educational Programme: Fundamental and Applied Linguistics (Bachelor)

Final Grade: 10

Year of Graduation: 2018

This research is devoted to the study of the connection between consciousness and verbal behavior of a person. The very phenomenon of consciousness is still not defined, but usually in psychology it is understood from a structural point of view. In this paper, consciousness is defined as a set of functions of human perception: logic, ethics, intuition and sensorics. According to the theory of Cal Jung, there are 4 types of consciousness, which depend on the development of these functions. The results of the functioning of consciousness are realized in speech, and 4 Jungian types (the so-called psychotypes) are obviously marked by certain speech signs. The aim of the study was to establish a correlation between the psychological and linguistic characteristics of an individual and to check the accuracy of the automatic definition of a person's psychotype by its speech characteristics. The material for the study was the texts of 240 respondents aged 19-30 years of both sexes who filled in the same questionnaire, suggesting a detailed answer to each question. The psychotype of each respondent according to Jung's classification was preliminarily determined using several psychological tests. The next stage was preprocessing and vectorization of texts of all psychotypes and training on the obtained database of the following classifiers: knn, svm, random forest, multilayer perceptron, biLSTM, GRU. These algorithms of machine learning showed different results for the scales of logic-ethics and intuition-sensorics. The maximum accuracy for determining intuitive sensors was 72% using the random forest algorithm. For the logic-ethics, the best result of 66% was shown by the neural network biLSTM.

Full text (added May 31, 2018)

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses