Pavel Ustin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Pavel Ustin has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Fail Mubarakovich Gafarov
Kazan Federal University, Kazan, Russia
6 shared publications - Leonid Popov
Kazan (Volga Region) Federal University
3 shared publications - Galim Vakhitov
Kazan Federal University
2 shared publications Leonid M. Popov
2 shared publicationsLeonid Popov
Kazan Federal University, Institute of Computational Mathematics and Information Technologies, 420008, Kazan, 35 Kremlyovskaya, Russia
2 shared publications- Leonid Popov
Kazan Federal University 18 Kremlyovskaya Street Kazan Russia
2 shared publications
Latest Publications
- Open Access
- 5 October 2026
- Published by Kazan Federal University in Russian Digital Libraries Journal
- Vol. 29 (6) , 2357-2370
Predicting Changes in Personality Behavior Under the Influence of an Interlocutor
The study of interactions between users of information systems is an urgent task in humanitarian and technical research. The paper presents the development of a regression model that predicts changes in the severity of the content components of a text under the influence of other people. The data source was short conversations (message triplets) between two users on social networks. The trained model is designed to be used as part of a cognitive architecture that reflects a model of a subject's behavior in a digital environment.
- 5 October 2026
- Published by Kazan Federal University in Russian Digital Libraries Journal
- Vol. 29 (6) , 2357-2370
Open AccessPredicting Changes in Personality Behavior Under the Influence of an Interlocutor
The study of interactions between users of information systems is an urgent task in humanitarian and technical research. The paper presents the development of a regression model that predicts changes in the severity of the content components of a text under the influence of other people. The data source was short conversations (message triplets) between two users on social networks. The trained model is designed to be used as part of a cognitive architecture that reflects a model of a subject's behavior in a digital environment.
- 4 July 2024
- Published by Bastas Publications in Online Journal of Communication and Media Technologies
- Vol. 14 (3) , e202442
The role of strategic online engagement and content curation in professional branding and career advancement on social media platforms
This study investigates role of social media user engagement metrics in predicting career success likelihoods using supervised machine learning techniques. With platforms like LinkedIn and VKontakte becoming pivotal for networking and advancement, user statistics have emerged as potential indicators of professional capability. However, research questions metric reliability considering impression management tactics and biases. While prior studies examined limited activity features, this analysis adopts a robust CatBoost model to gauge career success prediction from multifaceted social data combinations. The study utilizes user profiles of over 17,000 on a major Russian platform. Individuals are categorized by an algorithm accounting for factors like salaries, experience, and employment status. User statistics spanning engagement, content sharing, popularity, and profile completeness provide model inputs. Following comparative evaluation, CatBoost achieved superior performance in classification accuracy, precision, recall and ROC AUC score. Analysis of SHapley Additive exPlanations values provides explanatory modeling insights into influential metrics, thresholds, and patterns. Results reveal subscribers, reposts and interest pages as highly impactful, suggesting that influence and content resonance predict success better than sheer visibility indicators like multimedia volumes. Findings also point to optimal engagement ranges beyond which career prediction gains diminish. Additionally, profile completeness and regular posting are positive to a limit, while likes to have negligible effects. The study contributes more holistic, data-driven visibility into effective social media conduct for career advancement. It advocates prioritizing network cultivation, tactical self-presentation, shareable narratives and reciprocal relationships over metrics gaming. Findings largely validate strategic communication theory around impression management and relationship-building.
- 4 July 2024
- Published by Bastas Publications in Online Journal of Communication and Media Technologies
- Vol. 14 (3) , e202442
The role of strategic online engagement and content curation in professional branding and career advancement on social media platforms
This study investigates role of social media user engagement metrics in predicting career success likelihoods using supervised machine learning techniques. With platforms like LinkedIn and VKontakte becoming pivotal for networking and advancement, user statistics have emerged as potential indicators of professional capability. However, research questions metric reliability considering impression management tactics and biases. While prior studies examined limited activity features, this analysis adopts a robust CatBoost model to gauge career success prediction from multifaceted social data combinations. The study utilizes user profiles of over 17,000 on a major Russian platform. Individuals are categorized by an algorithm accounting for factors like salaries, experience, and employment status. User statistics spanning engagement, content sharing, popularity, and profile completeness provide model inputs. Following comparative evaluation, CatBoost achieved superior performance in classification accuracy, precision, recall and ROC AUC score. Analysis of SHapley Additive exPlanations values provides explanatory modeling insights into influential metrics, thresholds, and patterns. Results reveal subscribers, reposts and interest pages as highly impactful, suggesting that influence and content resonance predict success better than sheer visibility indicators like multimedia volumes. Findings also point to optimal engagement ranges beyond which career prediction gains diminish. Additionally, profile completeness and regular posting are positive to a limit, while likes to have negligible effects. The study contributes more holistic, data-driven visibility into effective social media conduct for career advancement. It advocates prioritizing network cultivation, tactical self-presentation, shareable narratives and reciprocal relationships over metrics gaming. Findings largely validate strategic communication theory around impression management and relationship-building.
- Open Access
- 3 July 2024
- Published by EDP Sciences in BIO Web of Conferences
- Vol. 116, 06010
RETRACTED: Methods of social network texts analysis for a psychometric model of personal behavior
See the retraction notice BIO Web of Conferences 116, 00001 (2024), https://doi.org/10.1051/bioconf/202411600001
- 3 July 2024
- Published by EDP Sciences in BIO Web of Conferences
- Vol. 116, 06010
Open AccessRETRACTED: Methods of social network texts analysis for a psychometric model of personal behavior
See the retraction notice BIO Web of Conferences 116, 00001 (2024), https://doi.org/10.1051/bioconf/202411600001
- 28 February 2024
- Published by HORS Publishing House, LLC in Общество: социология, психология, педагогика
- No. 2,p. 48-54
A Study of the Resilience of Foreign Students from Central Asian Countries during the Period of Adaptation at the University
This article reveals such an important psychological aspect during the period of adaptation of foreign students from Central Asian countries to higher education as resilience. The characteristic of the components of resili-ence in the form of indicators and leading components is given, with the help of which its role as the main core and resource of personality in the process of adaptation is confirmed. The aim of the work is to study the de-gree of vitality of foreign students from Central Asian countries with different types of adaptation to life difficul-ties. Psychological tests in the Russian language were chosen as the research methods, the participants of which were foreign students from three Central Asian countries studying in Russia. The authors analyzed the interrelation of the components of resilience and its importance in the process of adaptation of foreign students from Central Asian countries during their studies at Russian universities. The results of the study can be applied in the field of socio-psychological planning and forecasting.
- 28 February 2024
- Published by HORS Publishing House, LLC in Общество: социология, психология, педагогика
- No. 2,p. 48-54
A Study of the Resilience of Foreign Students from Central Asian Countries during the Period of Adaptation at the University
This article reveals such an important psychological aspect during the period of adaptation of foreign students from Central Asian countries to higher education as resilience. The characteristic of the components of resili-ence in the form of indicators and leading components is given, with the help of which its role as the main core and resource of personality in the process of adaptation is confirmed. The aim of the work is to study the de-gree of vitality of foreign students from Central Asian countries with different types of adaptation to life difficul-ties. Psychological tests in the Russian language were chosen as the research methods, the participants of which were foreign students from three Central Asian countries studying in Russia. The authors analyzed the interrelation of the components of resilience and its importance in the process of adaptation of foreign students from Central Asian countries during their studies at Russian universities. The results of the study can be applied in the field of socio-psychological planning and forecasting.
- 18 February 2024
- Published by Springer Nature
- p. 76-83
Development of an Indicator of Social Success of Social Network Users to Improve Intelligent Management Systems
- 18 February 2024
- Published by Springer Nature
- p. 76-83
Development of an Indicator of Social Success of Social Network Users to Improve Intelligent Management Systems
- 30 January 2024
- Published by Springer Nature
- p. 131-138
Interpretable Neural Network Models in School Teacher Success Prediction
- 30 January 2024
- Published by Springer Nature
- p. 131-138
Interpretable Neural Network Models in School Teacher Success Prediction
- Open Access
- 13 November 2023
- Published by LIDSEN Publishing Inc in OBM Neurobiology
- Vol. 07 (04) , 1-16
Assessment of a Person's Social Success Through the Characteristics of Interpersonal Relationships in A Virtual Environment
The sudden spread of the COVID-19 pandemic has convincingly proved the role of social networks in human life activity as an actor of interpersonal relations. The need for isolation and the limitation of face-to-face communication between people has significantly transformed the system of interpersonal connections through an extensive increase in social contacts in the virtual environment and the growing importance of online social services. In the study, we addressed the problem of diagnosing the indicator of social success of a personality, reflecting characteristics of its interpersonal relations in offline activity through the attributes of its virtual activity in social networks. The research was based on the methods of social network analysis and traditional ways of psychodiagnostics. Social networks were analyzed using social graphs - mathematical models that describe the characteristics of relationships between users in social networks through various metrics (friends, elements, edges, density, closeness centrality, degree centrality, clustering coefficient, etc.). The study aims to prove the predictive validity of social graph indicators as predictors of personality social success through correlations of graph characteristics reflecting the features of interpersonal relations of a social network user in a virtual environment with the socio-psychological hands of traditional psychodiagnostic tools. The study included 601 subjects. Data was collected using psychological questionnaires and personal profiles from the social network VKontakte. The results of the study showed correlations between several characteristics of social graphs (density, clustering coefficient, closeness centrality, etc.) and several indicators of psychodiagnostic techniques (Dominance index in relationships with others, Organizational abilities, Desire for people, Narcissism, etc.). The significant contribution of the research is to expand the methodological apparatus of psychological science and to open new methods of predicting interpersonal relations of personality through its activity in a virtual environment.
- 13 November 2023
- Published by LIDSEN Publishing Inc in OBM Neurobiology
- Vol. 07 (04) , 1-16
Open AccessAssessment of a Person's Social Success Through the Characteristics of Interpersonal Relationships in A Virtual Environment
The sudden spread of the COVID-19 pandemic has convincingly proved the role of social networks in human life activity as an actor of interpersonal relations. The need for isolation and the limitation of face-to-face communication between people has significantly transformed the system of interpersonal connections through an extensive increase in social contacts in the virtual environment and the growing importance of online social services. In the study, we addressed the problem of diagnosing the indicator of social success of a personality, reflecting characteristics of its interpersonal relations in offline activity through the attributes of its virtual activity in social networks. The research was based on the methods of social network analysis and traditional ways of psychodiagnostics. Social networks were analyzed using social graphs - mathematical models that describe the characteristics of relationships between users in social networks through various metrics (friends, elements, edges, density, closeness centrality, degree centrality, clustering coefficient, etc.). The study aims to prove the predictive validity of social graph indicators as predictors of personality social success through correlations of graph characteristics reflecting the features of interpersonal relations of a social network user in a virtual environment with the socio-psychological hands of traditional psychodiagnostic tools. The study included 601 subjects. Data was collected using psychological questionnaires and personal profiles from the social network VKontakte. The results of the study showed correlations between several characteristics of social graphs (density, clustering coefficient, closeness centrality, etc.) and several indicators of psychodiagnostic techniques (Dominance index in relationships with others, Organizational abilities, Desire for people, Narcissism, etc.). The significant contribution of the research is to expand the methodological apparatus of psychological science and to open new methods of predicting interpersonal relations of personality through its activity in a virtual environment.
- Open Access
- 1 November 2023
- Published by LIDSEN Publishing Inc in OBM Integrative and Complementary Medicine
- Vol. 08 (04) , 1-10
Possibilities of Predicting a Person's Substance Use Behaviour and Mental Health Through Social Media in a COVID-19 Crisis Context
The negative psychological consequences of the COVID-19 pandemic and the forced isolation of a large proportion of people worldwide have demonstrated the need to develop ways and technologies to reduce the effects of sudden threats of this type. The basis of any practical work to minimize the negative psychological consequences of the COVID-19 pandemic associated with substance use is the monitoring and diagnosis of the psychological resources of the individual. The article aims to show the possibilities of predicting the behavior of an individual through the content analysis of posts and reposts of their profile on the social network VKontakte on the example of the propensity to use psychoactive substances and to substantiate the possibilities of optimizing and automating such prediction through the use of category markers. Content analysis was carried out by latent semantic analysis of texts extracted from posts and reposts of VKontakte social network users with subsequent content analysis through selecting markers - category words. As a result, a categorical grid was built, which increases the efficiency of content analysis of posts and reposts of users and is suitable for further automation of such research by machine learning methods.
- 1 November 2023
- Published by LIDSEN Publishing Inc in OBM Integrative and Complementary Medicine
- Vol. 08 (04) , 1-10
Open AccessPossibilities of Predicting a Person's Substance Use Behaviour and Mental Health Through Social Media in a COVID-19 Crisis Context
The negative psychological consequences of the COVID-19 pandemic and the forced isolation of a large proportion of people worldwide have demonstrated the need to develop ways and technologies to reduce the effects of sudden threats of this type. The basis of any practical work to minimize the negative psychological consequences of the COVID-19 pandemic associated with substance use is the monitoring and diagnosis of the psychological resources of the individual. The article aims to show the possibilities of predicting the behavior of an individual through the content analysis of posts and reposts of their profile on the social network VKontakte on the example of the propensity to use psychoactive substances and to substantiate the possibilities of optimizing and automating such prediction through the use of category markers. Content analysis was carried out by latent semantic analysis of texts extracted from posts and reposts of VKontakte social network users with subsequent content analysis through selecting markers - category words. As a result, a categorical grid was built, which increases the efficiency of content analysis of posts and reposts of users and is suitable for further automation of such research by machine learning methods.
- Open Access
- 24 August 2023
- Published by LIDSEN Publishing Inc in OBM Neurobiology
- Vol. 07 (03) , 1-14
Analysis of Interpersonal Relationships of Social Network Users Using Explainable Artificial Intelligence Methods
The emergence of the social networking phenomenon and the sudden spread of the coronavirus pandemic (COVID-19) around the world have significantly affected the transformation of the system of interpersonal relations, partly shifting them towards virtual reality. Online social networks have greatly expanded the boundaries of human interpersonal interaction and initiated processes of integration of different cultures. As a result, research into the possibilities of predicting human behavior through the characteristics of virtual communication in social networks has become more relevant. The aim of the study is: to explore the possibilities of machine learning model interpretability methods for interpreting the success of social network users based on their profile data. This paper uses a specific method of explainable artificial intelligence, SHAP (SHapley Additive exPlanations), to analyze and interpret trained machine learning models. The research is based on Social Network Analysis (SNA), a modern line of research conducted to understand different aspects of the social network as a whole as well as its individual nodes (users). User accounts on social networks provide detailed information that characterizes a user's personality, interests, and hobbies and reflects their current status. Characteristics of a personal profile also make it possible to identify social graphs - mathematical models reflecting the characteristics of interpersonal relationships of social network users. An important tool for social network analysis is various machine learning algorithms that make different predictions based on sets of characteristics (social network data). However, most of today's powerful machine learning methods are "black boxes," and therefore the challenge of interpreting and explaining their results arises. The study trained RandomForestClassifier and XGBClassifier models and showed the nature and degree of influence of the personal profile metrics of VKontakte social network users and indicators of their interpersonal relationship characteristics (graph metrics).
- 24 August 2023
- Published by LIDSEN Publishing Inc in OBM Neurobiology
- Vol. 07 (03) , 1-14
Open AccessAnalysis of Interpersonal Relationships of Social Network Users Using Explainable Artificial Intelligence Methods
The emergence of the social networking phenomenon and the sudden spread of the coronavirus pandemic (COVID-19) around the world have significantly affected the transformation of the system of interpersonal relations, partly shifting them towards virtual reality. Online social networks have greatly expanded the boundaries of human interpersonal interaction and initiated processes of integration of different cultures. As a result, research into the possibilities of predicting human behavior through the characteristics of virtual communication in social networks has become more relevant. The aim of the study is: to explore the possibilities of machine learning model interpretability methods for interpreting the success of social network users based on their profile data. This paper uses a specific method of explainable artificial intelligence, SHAP (SHapley Additive exPlanations), to analyze and interpret trained machine learning models. The research is based on Social Network Analysis (SNA), a modern line of research conducted to understand different aspects of the social network as a whole as well as its individual nodes (users). User accounts on social networks provide detailed information that characterizes a user's personality, interests, and hobbies and reflects their current status. Characteristics of a personal profile also make it possible to identify social graphs - mathematical models reflecting the characteristics of interpersonal relationships of social network users. An important tool for social network analysis is various machine learning algorithms that make different predictions based on sets of characteristics (social network data). However, most of today's powerful machine learning methods are "black boxes," and therefore the challenge of interpreting and explaining their results arises. The study trained RandomForestClassifier and XGBClassifier models and showed the nature and degree of influence of the personal profile metrics of VKontakte social network users and indicators of their interpersonal relationship characteristics (graph metrics).
- Open Access
- 22 December 2022
- Published by National Research University, Higher School of Economics (HSE) in Voprosy Obrazovaniya / Educational Studies Moscow
- No. 4,p. 33-57
Grade Inflation in Schools During the COVID-19 Pandemic: Unexpected Effect or Anti-Crisis Strategy?
The closure of educational institutions and the transfer of the learning process to a distance format during the COVID-19 pandemic came as a shock to everyone involved in the educational process. There was, in fact, a rupture of the educational everyday — the normal and unproblematic order of things. A “new normal”, as it came to be called, could not emerge immediately — it had to be reconstructed within the unaccustomed contexts of distance interaction for many. Collective practices of this construction were and are captured today in the narratives of their participants — teachers, students and sometimes their parents. This study attempts, through quantitative analysis, to describe the transformation of assessment in schools during the pandemic and to formulate a hypothesis as to the possible reason for the change in marking practices as one of the most significant ways of managing the learning process as well as the social and psychological context of its implementation. The data source used was a database of students’ grades from schools in one of the regions of the Russian Federation, accumulated from 2015 to 2021. Using big data methods and the Cohen effect coefficient, the main changes in assessment are described. Particular attention is paid to the few months of 2020, when all schools in the region were closed to face-to-face attendance. It is during this period that a significant inflationary spike in marking is recorded. It is suggested that teachers deliberately use the strategy of inflating marks in order to maintain a favorable social and psychological climate in school classes and to reduce the general tension in connection with the transition to the distance learning format. An attempt has been made to theorize a strategy for the grade inflation behavior during a period of cataclysm.
- 22 December 2022
- Published by National Research University, Higher School of Economics (HSE) in Voprosy Obrazovaniya / Educational Studies Moscow
- No. 4,p. 33-57
Open AccessGrade Inflation in Schools During the COVID-19 Pandemic: Unexpected Effect or Anti-Crisis Strategy?
The closure of educational institutions and the transfer of the learning process to a distance format during the COVID-19 pandemic came as a shock to everyone involved in the educational process. There was, in fact, a rupture of the educational everyday — the normal and unproblematic order of things. A “new normal”, as it came to be called, could not emerge immediately — it had to be reconstructed within the unaccustomed contexts of distance interaction for many. Collective practices of this construction were and are captured today in the narratives of their participants — teachers, students and sometimes their parents. This study attempts, through quantitative analysis, to describe the transformation of assessment in schools during the pandemic and to formulate a hypothesis as to the possible reason for the change in marking practices as one of the most significant ways of managing the learning process as well as the social and psychological context of its implementation. The data source used was a database of students’ grades from schools in one of the regions of the Russian Federation, accumulated from 2015 to 2021. Using big data methods and the Cohen effect coefficient, the main changes in assessment are described. Particular attention is paid to the few months of 2020, when all schools in the region were closed to face-to-face attendance. It is during this period that a significant inflationary spike in marking is recorded. It is suggested that teachers deliberately use the strategy of inflating marks in order to maintain a favorable social and psychological climate in school classes and to reduce the general tension in connection with the transition to the distance learning format. An attempt has been made to theorize a strategy for the grade inflation behavior during a period of cataclysm.