Allocation of the scientific directions of development of science and technologies center in oil and gas industry based on the co-authorship network

Fedor Krasnov, Mars Khasanov


Planning of scientific and technological development research organizations should not be divorced from the real situation. Phenomena such as organizational inertia, diversification of research and the hobby of creating IT products can significantly distort any strategies and development plans. However, the feasibility of the plans is an important characteristic of development, significantly reinforcing the motivation for the result. So setting realistic goals is essential.

Quantitative tools for assessing the implementation of scientific research may not be enough. The formal paper reporting the research is not able to reflect the passion and engagement of researchers in the work. While, small-scale research such as presentations at scientific conference or a scientific paper in a peer-reviewed periodical journal require significantly more casual attitude on the part of researchers.

Analysis of the development of scientific and technological organizations based on publication activity is a common practice. Many studies analyse a corpus of texts of scientific articles and draw conclusions about the development trends. Textual data have a high noise level and even modern methods of analysis such as LDA and Word2Vec give accurate predictions only based on huge volumes of texts that were not always available to small organizations. Namely, a small research organization suffer more from inaccuracies of the planning of scientific activities.

The authors of this study propose to take advantage of the analysis of the articles (presentations) based on a bipartite graph of co-authorship to highlight research directions for further evaluation and planning.

Full Text:

PDF (Russian)


Kaufman L., Rousseeuw P. J. Finding groups in data: an introduction to cluster analysis. – John Wiley & Sons, 2009. – Т. 344.

Ng R. T., Han J. CLARANS: A method for clustering objects for spatial data mining //IEEE transactions on knowledge and data engineering. – 2002. – Т. 14. – №. 5. – С. 1003-1016.

Ester M. et al. A density-based algorithm for discovering clusters in large spatial databases with noise //Kdd. – 1996. – Т. 96. – №. 34. – С. 226-231.

Guha S., Rastogi R., Shim K. Cure: an efficient clustering algorithm for large databases //Information Systems. – 2001. – Т. 26. – №. 1. – С. 35-58.

Guha S., Rastogi R., Shim K. ROCK: A robust clustering algorithm for categorical attributes //Information systems. – 2000. – Т. 25. – №. 5. – С. 345-366.

Karypis G., Han E. H., Kumar V. Chameleon: Hierarchical clustering using dynamic modeling //Computer. – 1999. – Т. 32. – №. 8. – С. 68-75.

Lv Y., Zhai C. X. Adaptive term frequency normalization for BM25 //Proceedings of the 20th ACM international conference on Information and knowledge management. – ACM, 2011. – С. 1985-1988.


Abava  Кибербезопасность MoNeTec 2024

ISSN: 2307-8162