The aim of the study is to develop a questionnaire integrating traditional career guidance techniques and categorization of IT professions by analyzing existing classifications and interviewing IT specialists. Methods. In order to achieve the objective, we selected a traditional career guidance methodology by analysing the existing ones and selecting the one that best corresponds to the research objective; we also selected a system of categorisation of IT specialties by analysing the existing classifications and interviewing IT specialists. Results. Among the existing traditional career guidance techniques, the Holland Test was selected as having the potential to be adapted to the IT field. The analysis of the existing classifications of IT specialities showed the lack of unity, in this context our own categorisation was developed, including five main categories: development, QA specialists, working with data and research, management, design. Conclusions. Based on the results of the study, it was hypothesised that there are differences in the degree of expression of the Holland types among the different IT professions. Also, the presumed correspondence between different categories of IT professions and the predominant Holland types is given. The study forms the basis for the development of a software product that will help people to identify the most suitable IT professions for them.

Online social media has an increasing influence on people’s lives, providing tools for communication and self–representation. People’s digital traces are gaining attention as a reflection of their personality traits, enhancing the personality computing tasks in various areas. This study aims at the identification of statistical associations between psychometric scores from three questionnaires—the Big Five Inventory, Plutchik’s Lifestyle Index and the Eysenck Personality Questionnaire—and a set of graphical features of avatar images from the VK online social media that include the pixel characteristics from the HSV and RGB color models and the number of persons and faces depicted in an avatar. The problem is considered from the statistical point of view. The dependency between psychometric scores and the number of faces/persons is assessed with the Kruskal–Wallis test with Dunn test pairwise comparisons. The color-pixel characteristics that are associated with the psychometric scores are selected with several fits of the regularized regression with L2 and MCP penalties. The data for the study were collected via a specially developed application for the online social media platform VK. The results of the analysis support existing research on how colors express personality and discover certain color-pixel image characteristics that could be used for personality computing models.

The paper discusses the lack of automated systems that provide personalized career advice without the need for traditional career guidance tests or counselling sessions. It suggests analysing social media data, specifically the topics of the user subscriptions, could be used to generate personalized career recommendations. The article proposes the use of the RIASEC test to identify the mean RIASEC profile of users with the same leading subscription topic. The study to test the hypothesis that the RIASEC codes vary for leading group subscriptions in terms of frequencies of appearance in the upper and lower triades and in terms of the mean scores. The research methods are statistical analysis, namely the chi-squared test for homogeneity with the Bayesian Factor and the Kruskall-Wallis test. The statistical analysis confirms the existence of RIASEC score patterns for leading group topics, and for several leading subscription topics the patterns of the environment RIASEC profile were established. The findings of the study can be used to develop decision making intelligent system that utilize social media data to provide personalized career guidance.

Digital traces of the social media users acquire a lot of attention nowadays as they may serve as predictors for various personality traits. The paper refers to the analysis of graphical digital traces, expressed by the user avatars, and aims at quantification of the relationship between its color and semantic characteristics and user’s psychological tests results. The Big Five Inventory and Eysenck Personality Questionnaire were considered. The sample of 548 observations, containing the user’s scores from the questionnaires along with the depersonalized open–access information from their profiles, was collected with the use of a freely accessible application in the online social media VK. The graphical characteristics from the HSV color model of the avatar images were obtained. Clusters of users with similar profiles of the psychometric scores were identified, allowing for easy interpretation. The conceptual Bayesian belief network was proposed for the dependency between groups of users with similar psychometric scores profile and the graphical characteristics of users’ avatar image. The results of the paper are primarily intended for use in the automated systems for the personality computing on the base of their digital traces.