In this paper, we present an approach to solving the problem of choosing the most probable configuration of missed meta-profile values of the user, such as the home city, year of birth, city of residence, etc. To solve this problem, data from social networks obtained from alternative sources - the social environment of the user, his personal data, data from his accounts in other social networks. Various combinations of approaches to the choice of hypotheses about the values of the missed meta-profile parameters of the user are considered.