Advanced text-mining for trend analysis of Russia's Extractive Industries. (January 2020)

• Record Type: Journal Article
• Authors: Gokhberg, Leonid; Kuzminov, Ilya; Khabirova, Elena; Thurner, Thomas
• Is Part Of: Futures. Volume 115(2020)
• Publication Date: 2020-01
• Subjects: Extractive industries -- Mineral sector -- New technologies -- Technology foresight -- Horizon scanning -- Text-mining -- Science -- Technology and innovation -- Russian Federation -- Critical technologies; Economic forecasting -- Periodicals; Technological forecasting -- Periodicals; Economic policy -- Periodicals; Prévision économique -- Périodiques; Prévision technologique -- Périodiques; Politique économique -- Périodiques; Economic forecasting; Economic policy; Technological forecasting; Periodicals; Electronic journals; 330.0112
• DOI: 10.1016/j.futures.2019.102476
• Languages: English
• ISSNs: 0016-3287

Abstract

Highlights: Russia's extractive industry seeks local technologies to replace expensive technology-intense imports. Russia sees opportunities to become a prominent provider of specialized equipment and services for the production of oil, gas. To identify technological developments, Russia is increasingly building competencies around foresight activities. Presented foresight study combines the subjective opinions gathered through expert workshops with text-mining techniques. The presented methodology helped to link the technologies to dominant professional discussions and to flag key trends. Abstract: The world economy relies on access to industrial metals, oil and gas for maintaining its critical industrial infrastructure. Although demand is likely to remain high, the most accessible deposits have been depleted. Future capacity growth will be facilitated through further technological developments. Russia as a leading producer is paying great attention to strengthening its competitive edge in global markets. This paper reports on a large-scale technology foresight study of the Russian extractive sector (including oil and gas), which combined expert-based foresight activities with statistical analyses and text-mining techniques based on artificial intelligence and machine learning technologies. The presented methodology helped to link the technologies to dominant discussions (e.g. climate change vs rural development) and to flag key trends. Furthermore, quantitative estimates can be identified quickly. The study's methodology should function as an example for similar studies to support policy planning and investment decisions based on text-mining techniques.