Predicting the results of the R. Cattell test based on the social network user profiles

Digital footprints of users in the social network and the results of passing the 16-factor R. Cattell test. The method consists in applying statistical methods and relevant machine learning algorithms to personal data on the user's page. The main results of the experiment are the identification of a significant correlation between the factors evaluated by the R. Cattell test and digital footprints, and the construction of predictive models. The best results among the machine learning methods for predicting the results of the R. Cattell test were shown by gradient boosting algorithms with the maximum valueof the F1-micro metric of 0.606, which was achieved on the factor “emotional sensitivity” (factor I). The practical significance of the work lies in the development of a tool for automatically predicting the results of the R. Cattell test based on the user's digital footprints. The theoretical significance lies in the development of a method for the automated evaluation of the expression of personality traits of social network users on their digital footprints.