Comparative analysis of the topics of scientific publications in the field of artificial intelligence in international and Russian journals

Abstract

Aim. To perform a comparative analysis of the topics and volumes of publication activity in the field of artificial intelligence (AI) of Russian authors in journals indexed in such databases as the Russian Science Citation Index (RSCI) and WoS/Scopus, in relation to the fields of AI technologies, scientific directions and organisations of the place of work.Tasks. To create a list of publications by authors with Russian affiliation in journals indexed in WoS/Scopus, including those categorised as Q1 and Q2 quartiles, as well as in the proceedings of A* level conferences, the topics of which are related to the AI sphere; to create a list of publications by Russian researchers devoted to the AI topics in journals indexed in RSCI, including those categorised as Q1; to carry out a comparative analysis of the topics and structure of publications by Russian authors in journals indexed in WoS/Scopus and RSCI in relation to the fields of AI technologies, groups of scientific specialties, and organisations of the authors’ place of work.Methods. The methodology of the study is based on expert analysis of publications in scientific journals indexed in WoS/Scopus, including Q1 and Q2 quartiles, in proceedings of A* level conferences, scientific journals indexed in RSCI for 2017–2021, the subject matter of which relates to the field of AI, based on selections from open databases of publications using libraries and packages for data processing and analysis. The criterion for attributing an article to the AI subject was the presence of word combinations from the fields of AI technologies and subtechnologies in the search fields “publication title” and (or) “Keywords”, “Abstract”.Results. Comparison of highly rated WoS/Scopus, Q1, Q2, A* and RINC K1 publications shows that among WoS/Scopus, Q1, Q2, A* publications “Machine learning: knowledge representation, ontology, interpretation, explanation” (32 %) and “Computer vision” (30 %) dominate. Among RINC Q1 publications, “Responsible Artificial Intelligence (ethics and philosophy, legal regulations, security)” (34 %), “Machine learning: knowledge representation, ontology, interpretation, explanation” (28 %) and “Intelligent analysis of data and processes, making sense of patterns” (13 %) dominate.Conclusions. The analysis of publication activity of Russian authors in relation to AI topics on the basis of comparison of scientific publications from WoS/Scopus and RINC databases can serve as an information basis for selection of AI competence centres and formation of lists of best practices in the field of AI.