Abstract
This paper discusses the technical details of obtaining and processing data to determine a set of characteristics of texts from social networks, genre preferences in movies and music genres for students of Kazan Federal University who have different academic performance (successful, average, not-successful). The selection of such characteristics is carried out using machine learning methods (Word2Vec, tSNE). The data obtained is used in the development of a functional psychometric model of cognitive behavioral predictors of an individual’s activity within the framework of their educational activities. We also developed a web application for visualizing the obtained data using the Flask engine.
Highlights
The analysis of psychological characteristics of a person is a problem that has received a lot of attention in the past few years
One of the sources of quantitative and qualitative data in our project is the social network Vkontakte, as it is a huge repository of personalized user data, among which we can distinguish the majority of current students and potential applicants of our University
We have identified the properties of texts and genre preferences in music and film among students with different levels of academic performance
Summary
The analysis of psychological characteristics of a person is a problem that has received a lot of attention in the past few years. The development of information technologies, methods of mathematical statistics and processing of large data sets gave a noticeable boost to the development of this topic. One of the applications of this system is to predict the success of students of Kazan Federal University. Current results of our projects are described in [1,2,3,4]. One of the sources of quantitative and qualitative data in our project is the social network Vkontakte, as it is a huge repository of personalized user data, among which we can distinguish the majority of current students and potential applicants of our University. In most cases, the mentioned data is either unstructured (such as the texts of posts on users’ walls), so it is necessary to use methods for automatic processing of information
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
