Development of textual analytics tools for analysis of public and specialized sources in the tasks of foresight and system analysis

Abstract

A combined approach to extracting concepts and constructing classifiers and ontologies using open and proprietary software packages has been developed. Modern approaches, methods and models of storing large amounts of poorly structured information from Open Source software sets are studied. An ontology was built, in the leaves of which a classifier based on Boolean rules was implemented using SAS(R) Content Categorization Software. To build the ontology, the approach of constructing vectors of related concepts is employed using the Open Source library of Gensim software, namely the Word2Vec model. A typical algorithm for constructing a classifying ontology has been developed. The results of the research can be used to build an ontology of subject areas, create classification ontologies and mark corpora of texts.