Use of big data in schoolchildren’s career guidance practices for the medical profession

Abstract

Introduction. The healthcare staffing deficiency affects negatively the availability and quality of medical aid and, consequently, the people’s quality of life and well-being. To eliminate this deficiency, it is proposed to use new formats and tools for schoolchildren’s professional orientation towards medical professions. Purpose of the study: to identify the potential of using big data for the development of schoolchildren’s career guidance practices in the field of medical labour. Materials and methods. The research was grounded on the identification of the pattern of the medical community’s personal and professional interests, as based on the data of the digital footprint of medical workers, first and final year students of Federal state-funded educational institution of higher education “Siberian State Medical University” (hereinafter SibSMU) [Russian Federation]. The technology “Pixel” borrowed from the social network “VKontakte” was used for the study. The study involved 947 persons whose personal data formed a basis for constructing a pattern of medical community interests. The study involved the methods of theoretical and structural analysis, predictive analytics and simulation modelling based on neural network data, as well as parsing. Results. A total of 6 attributes of the target audience segmentation (the medical community) were revealed; several identification features (explicit and implicit) reflecting the involvement of the social network “VKontakte” users in the medical community were found, analysed and differentiated on the basis of marketing approach. Using the “Pixel” technology, 3 sublevels reflecting the users’ explicit professional-interest category and 184 characteristics underlying their formation were found. Using the base of the social network “VKontakte”, a total of 79 million pages of users were processed according to the identification features. It was found that 79 thousand people matched the obvious professional interest reflecting the category “Medicine”. The authors undertook a search and analysis of the interests of the first-year (937 people) and final-year students of SibSMU as well as of professionals (medical doctors with more than 5 years of service record), following which a pattern of interests pertaining to the category of implicit identifying characteristics that included 14 categories was revealed. Conclusion. The research results showed that the use of big data and the analysis of the medical community’s digital footprint is an effective tool for the development of career guidance practices for schoolchildren and their parents. The identification of patterns of the medical community’s personal and professional interests can be used for the improvement of the efficiency of career guidance work with schoolchildren towards their motivated choice of the medical sphere as a career vector. The work with big data, complementing the existing career guidance approaches, is a due way to understand the preferences and interests of every schoolchild, which is important for achieving personalised support of professional self-identification.