This paper discusses some approaches to intellectual text analysis in application to automated monitoring of the labour market. The construction of an analytical system based on Big Data technologies for the labour market is describedd. Were compared the combinations of methods of extracting semantic information about objects and connections between them (for example, from job advertisements) from specialized texts. A system for monitoring the Russian labour market has been created, and the work is underway to include other countries in the analysis. The considered approaches and methods can be widely used toextract knowledge from large amounts of texts.
The article discusses the methods and algorithms that underlie the analytical platform for automated monitoring and analysis of the labor market in the Russian Federation, as well as the analysis of the higher education system's compliance with the labor market's current needs. The study involved natural language processing methods and Big Data technologies. The general scheme corresponds to end-to-end processing -from data collection and storage, their transformation, analysis, and modeling, to visualization of results and decision-making. The analytical core of the system is a module for intellectual analysis of the texts of job advertisements in the labor market. The vacancies are collected from the most complete databases in Russia (namely HeadHunter, Work in Russia and SuperJob). Job descriptions of vacancies are matched with the official list of professions of the Ministry of Labor and Social Protection of Russia using semantic analysis based on neural models trained on large arrays of texts. Also, using semantic analysis, automated monitoring and intellectual analysis of the staffing needs of the all-Russian and regional labor markets are carried out according to the range of specialties of the university. Data gathering has been ongoing from 2015 up to now.
Started in natural sciences, the high demand for analyzing a vast amount of complex data reached suchresearch areas as economics and social sciences. Big Data methods and technologies provide newefficient tools for research. In this paper, we discuss the main principles and architecture of the digitalanalytical platform aimed to support socio-economic applications. Integrating specific open-sourcesolutions, the platform intended to cover full-cycle data analysis and machine learning experiments,from data gathering to visualization. One of the system's primary goals is to deliver the advantage ofthe cloud and distributed computing and GPU accelerators with Big Data analysis techniques. Theauthors present the approach of building the platform from low-level services such as storage, virtualinfrastructure, pass-through authentication, up to data flows processing, analysis experiments, andresults representation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.