Working paper
Centrality Measures in Networks based on Nodes Attributes, Long-Range Interactions and Group Influence
Methods of network analysis are used in this paper for mapping the local academic community of St. Petersburg sociologists. The survey data on relations between individual scholars serve as a guide in reconstruction of the communitys network history as well as a system of independent variables in accounting for differences between its various natural zones. In this manner, the paper explores the points of convergence between Chicago school social ecology and modern social network analysis.
This volume contains two types of papers—a selection of contributions from the “Second International Conference in Network Analysis” held in Nizhny Novgorod on May 7–9, 2012, and papers submitted to an "open call for papers" reflecting the activities of LATNA at the Higher School for Economics.
This volume contains many new results in modeling and powerful algorithmic solutions applied to problems in
- vehicle routing
- single machine scheduling
- modern financial markets
- cell formation in group technology
- brain activities of left- and right-handers
- speeding up algorithms for the maximum clique problem
- analysis and applications of different measures in clustering
The broad range of applications that can be described and analyzed by means of a network brings together researchers, practitioners, and other scientific communities from numerous fields such as Operations Research, Computer Science, Bioinformatics, Medicine, Transportation, Energy, Social Sciences, and more. The contributions not only come from different fields, but also cover a broad range of topics relevant to the theory and practice of network analysis. Researchers, students, and engineers from various disciplines will benefit from the state-of-the-art in models, algorithms, technologies, and techniques including new research directions and open questions.
This volume contains proceedings of the fourth conference on Analysis of Images, Social Networks and Texts (AIST’2015)1 . The first three conferences in 2012–2014 attracted a significant number of students, researchers, academics and engineers working on interdisciplinary data analysis of images, texts, and social networks. The broad scope of AIST makes it an event where researchers from different domains, such as image and text processing, exploiting various data analysis techniques, can meet and exchange ideas. We strongly believe that this may lead to crossfertilisation of ideas between researchers relying on modern data analysis machinery. Therefore, AIST brings together all kinds of applications of data mining and machine learning techniques. The conference allows specialists from different fields to meet each other, present their work, and discuss both theoretical and practical aspects of their data analysis problems. Another important aim of the conference is to stimulate scientists and people from the industry to benefit from the knowledge exchange and identify possible grounds for fruitful collaboration. The conference was held during April 9–11, 2015. Following an already established tradition, the conference was organised in Yekaterinburg, a cross-roads between European and Asian parts of Russia, the capital of Urals region.The key topics of AIST are analysis of images and videos; natural language processing and computational linguistics; social network analysis; pattern recognition, machine learning and data mining; recommender systems and collaborative technologies; semantic web, ontologies and their applications. The Program Committee and the reviewers of the conference included wellknown experts in data mining and machine learning, natural language processing, image processing, social network analysis, and related areas from leading institutions of 22 countries including Australia, Bangladesh, Belgium, Brazil, Cyprus, Egypt, Finland, France, Germany, Greece, India, Ireland, Italy, Luxembourg, Poland, Qatar, Russia, Spain, The Netherlands, UK, USA and Ukraine.
The article introduces a historical-sociological research project reconstructing intellectual and institutional transformations of post-soviet social sciences in the last 25 years. The projects ambition was to achieve this aim via applying classical community study research strategy and various methods derived from social science history to the case of St. Petersburg sociologists. We identified 622 individuals as St. Petersburg sociologists and traced records of their institutional trajectories, appearance in print, citing behaviour, social networks, political attitudes, sources of income, professional authorities, and attention spaces through 25 years.
This volume contains a selection of contributions from the "First International Conference in Network Analysis," held at the University of Florida, Gainesville, on December 14-16, 2011. The remarkable diversity of fields that take advantage of Network Analysis makes the endeavor of gathering up-to-date material in a single compilation a useful, yet very difficult, task. The purpose of this volume is to overcome this difficulty by collecting the major results found by the participants and combining them in one easily accessible compilation.
The current paper aims to present the Scan-4-Light study, which was conducted for the systematic scanning and analysis of the Searchlight newsletters as a rapidly growing collection of articles on trends and topics in development and poverty. Built upon the concept of the systemic foresight methodology, the Scan-4-Light approach involves the integrated use of horizon scanning, network analysis and evolutionary scenarios combined with expert consultations and workshops. The study identified the emerging trends, issues, weak signals and wild cards; created high-value visualisations to emphasize the results and findings; and produced narratives to increase the impact and awareness of the development issues. The Scan-4-Light project has resulted in a large number of specific outputs, providing the views of the Searchlight newsletters' contents at various levels of granularity. It has set out to show how the tools used here can be applied to illustrate the relationships among issues, and how these vary across countries and regions over time, and are linked to various stakeholders and possible solutions to problems. Scan-4-Light demonstrates how foresight tools and techniques can be used for the analysis of complex and uncertain issues, such as development and poverty, in a systemic way. The Scan-4-Light approach can be applied in a number of areas for scanning and identifying emerging trends and issues, and understanding the relationships between systems and solutions. The paper gives evidence that most of the issues, if not all, related to development are not isolated, but interlinked and interconnected. They require more holistic understanding and intervention with an effective collaboration between stakeholders.
Classical change-point detection procedures assume a change-point model to be known and a change consisting in establishing a new observations regime, i.e. the change lasts infinitely long. These modeling assumptions contradicts applied problems statements. Therefore, even theoretically optimal statistics in practice very often fail when detecting transient changes online. In this work in order to overcome limitations of classical change-point detection procedures we consider approaches to constructing ensembles of change-point detectors, i.e. algorithms that use many detectors to reliably identify a change-point. We propose a learning paradigm and specific implementations of ensembles for change detection of short-term (transient) changes in observed time series. We demonstrate by means of numerical experiments that the performance of an ensemble is superior to that of the conventional change-point detection procedures.
Semantic network reduction is considered in application to visual analytics of relational data. Merging structurally equivalent nodes it is straightforward to construct a reduced semantic network that completely speci es the initial structure of relations between nodes. This paper presents the analysis of such reduction applied to the communication network from Stanford Large Network Dataset Collection. It is shown how the reduction based on structural equivalence can help in visualization of large semantic networks.
Smoking is a problem, bringing signifi cant social and economic costs to Russiansociety. However, ratifi cation of the World health organization Framework conventionon tobacco control makes it possible to improve Russian legislation accordingto the international standards. So, I describe some measures that should be taken bythe Russian authorities in the nearest future, and I examine their effi ciency. By studyingthe international evidence I analyze the impact of the smoke-free areas, advertisementand sponsorship bans, tax increases, etc. on the prevalence of smoking, cigaretteconsumption and some other indicators. I also investigate the obstacles confrontingthe Russian authorities when they introduce new policy measures and the public attitudetowards these measures. I conclude that there is a number of easy-to-implementanti-smoking activities that need no fi nancial resources but only a political will.
One of the most important indicators of company's success is the increase of its value. The article investigates traditional methods of company's value assessment and the evidence that the application of these methods is incorrect in the new stage of economy. So it is necessary to create a new method of valuation based on the new main sources of company's success that is its intellectual capital.
We address the external effects on public sector efficiency measures acquired using Data Envelopment Analysis. We use the health care system in Russian regions in 2011 to evaluate modern approaches to accounting for external effects. We propose a promising method of correcting DEA efficiency measures. Despite the multiple advantages DEA offers, the usage of this approach carries with it a number of methodological difficulties. Accounting for multiple factors of efficiency calls for more complex methods, among which the most promising are DMU clustering and calculating local production possibility frontiers. Using regression models for estimate correction requires further study due to possible systematic errors during estimation. A mixture of data correction and DMU clustering together with multi-stage DEA seems most promising at the moment. Analyzing several stages of transforming society’s resources into social welfare will allow for picking out the weak points in a state agency’s work.