As a result of the latest changes in the Russian legislation concerning the IT sphere, controlling the content of information resources has become a headache of hosting services providers. This report offers an approach to solving this problem. We are going to present a system that enables the provider to carry out the step-by-step analysis of the content of a resource (preliminary filtering, thematic classification, genre analysis, decision making). The system can be customized for various subject domains.
The report will be interesting to the organizations involved in the text information analysis or the provision of hosting services. The audience will be able to estimate the approaches to text processing used in the project as a kind of alternative to Big Data analysis. The report is intended for audience with the average level of attainment.
Head of laboratory, Novosibirsk State University
Ph.D., the head of laboratory of A.P. Ershov Institute of informatics systems of Siberian Branch of Russian Academy of Sciences, associate professor of Novosibirsk State University.
He has scientific results in the following areas: knowledge representation and engineering, expert and decision support system, ontological modeling, ontology-based development of intelligent system, thesaurus development and natural language processing.
He has published about 200 scientific papers.
2000-2007 – Director of Novosibirsk branch of the Russian Research Institute of Artificial Intelligence.
1990 – till now – researcher, head of Artificial Intelligence laboratory (2005) of A.P. Ershov Institute of informatics systems of SB RAS.
1998 – till now – associate professor of Novosibirsk State University, the Department of Information Technology.