With the rapid development of mobile technologies, analyzing data generated by mobile devices is becoming increasingly important. A wide range of applications, from marketing to healthcare, require the development of effective methods for extracting valuable information from this data. This study is devoted to developing a methodology for assessing an individual's social capital based on the analysis of mobile communication data. To assess social capital, we propose a two-stage Cascade Model that combines the advantages of the Random Forest (RF) and Logistic Regression (LR) algorithms. In the first stage, RF is used to select the most significant features reflecting various aspects of social capital. In the second stage, LR is used to assess of social capital, taking into account nonlinear relationships between features. The results of the study open up new opportunities for studying social phenomena and can be used in as sociology, marketing, and urban planning.

The article is devoted to a brief review of approaches to the analysis of social relations in social networks using comments and credentials located in the profiles of social network users. The study aims to determine the interest and behavior of each user. The approach that we propose to determine the interests of social network users requires some methods of machine learning (classification analysis and data clustering). A method based on sentiment analysis and a naive Bayesian classifier is proposed. Determining the interests of social network users based on the intellectual analysis of comments can help to understand the logic of their behavior, and determine social relations between users and problems in society.

Social network analysis is a widely used technique to analyze relationships among wiki-users in Wikipedia. In this paper the method to identify hidden social networks participating in information conflicts in wiki-environment is proposed. In particular, we describe how text clustering techniques can be used for extraction of hidden social networks of wiki-users caused information conflict. By clustering unstructured text articles caused information conflict we create social network of wiki-users. For clustering of the conflict articles a hybrid weighted fuzzy-c-means method is proposed.