Book
IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)
ASONAM '20: International Conference on Advances in Social Networks Analysis and Mining, 7-10 December 2020, The Hague, Netherlands (Virtual).
The problem of community detection in a network with features at its nodes takes into account both the graph structure and node features. The goal is to find relatively dense groups of interconnected entities sharing some features in common. We apply the so-called data recovery approach to the problem by combining the least-squares recovery criteria for both, the graph structure and node features. In this way, we obtain a new clustering criterion and a corresponding algorithm for finding clusters one-by-one, so that the process can be interpreted as that of detecting communities indeed. We show that our proposed method is effective on real-world data, as well as on synthetic data involving either only quantitative features or only categorical attributes or both. In the cases at which attributes are categorical, state-of-the-art algorithms are available. Our algorithm appears competitive against them
The problem of community detection in a network with features at its nodes takes into account both the graph structure and node features. The goal is to find relatively dense groups of interconnected entities sharing some features in common. We apply the so-called data recovery approach to the problem by combining the least-squares recovery criteria for both, the graph structure and node features. In this way, we obtain a new clustering criterion and a corresponding algorithm for finding clusters one-by-one, so that the process can be interpreted as that of detecting communities indeed. We show that our proposed method is effective on real-world data, as well as on synthetic data involving either only quantitative features or only categorical attributes or both. In the cases at which attributes are categorical, state-of-the-art algorithms are available. Our algorithm appears competitive against them
Trading processes is a vital part of human life and any unstable situation results in the change of living conditions of individuals. We study the power of each country in terms of produce trade. Trade relations between countries are represented as a network, where vertices are territories and edges are export flows. As flows of products between participants are heterogeneous we consider various groups of substitute goods (cereals, fish, vegetables). We detect key participants affecting food retail with the use of classical centrality measures. We also perform clustering procedure in order to find communities in networks.
Proceedings of Machine Learning Research: Volume 97: International Conference on Machine Learning, 9-15 June 2019, Long Beach, California, USA
The problem of community detection in a network with features at its nodes takes into account both the graph structure and node features. The goal is to find relatively dense groups of interconnected entities sharing some features in common. Existing approaches require the number of communities pre-specified. We apply the so-called data recovery approach to allow a relaxation of the criterion for finding communities one-by-one. We show that our proposed method is effective on real-world data, as well as on synthetic data involving either only quantitative features or only categorical attributes or both. In the cases at which attributes are categorical, state-of-the-art algorithms are available. Our algorithm appears competitive against them.
The creation of software of analyst workplace supporting the mining process large amounts of statistical data of science, education and innovation are discussed in the paper. A hybrid approach, to the integration of classical methods of mathematical correlation analysis, pattern analysis and time series, as well as the interpretation of the results is provided. Particular attention is paid to the business processes to identify trends and changes in indicators, atypical dynamics of indicators and to the definition of «Best Performance» indicators vectors.
[EN] Introduction. Features of political communication in Russian-speaking segment of the Facebook network are analyzed in the article. According to researchers unlike their counterparts in the U.S. and elsewhere, Russian bloggers prefer platforms that combine features typical of blogs with features of social network services like Facebook. Objectives. The objectives were: classification of actors in the political groups in the Russian-speaking segment of Facebook and analysis of their sociolinguistic behavior. Method. The interdisciplinary analysis based on scope of politically active groups (N 200) and actors (N 291) during January – May, 2014. Results. Actors were classified by politic opinions into mainstream, oppositional and nationalist Clusters and based on network activity into designers of communication space, manipulators, graphomaniacs and local cluster authors. Their communicative and speech behavior was also analyzed and shown shaped specific virtual identities, which demonstrate distinguished sociolinguistic behavior. Discussion and Conclusion. Today the analysis of communication processes in politically active communities in the network environment is of great importance as the virtual sphere becomes more and more significant for achieve of various political aims both in Russia and around the world. The prospect of an actual study is to identify the ratio of online and off-line communication activity of actors in the political sphere in the Russian segment of Facebook.
This book constitutes the proceedings of the 5th International Conference on Analysis of Images, Social Networks and Texts, AIST 2016, held in Yekaterinburg, Russia, in April 2016. The 23 full papers, 7 short papers, and 3 industrial papers were carefully reviewed and selected from 142 submissions. The papers are organized in topical sections on machine learning and data analysis; social networks; natural language processing; analysis of images and video.