Michael Charnine

Dr. Michael Charnine


Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2021
Verified
Conference Paper
Closed access
MCMichael Charnine
Michael Charnine
ATAlexey Tishchenko
Alexey Tishchenko
LKLeon Kochiev
Leon Kochiev
This paper presents the results of a method for the visualization of the long-term prediction of research trending topics. Meaningful topics were identified among the words included in the titles of scientific articles. The title is the most important element of a scientific article and the main indication of the article’s subject and topic. We treated the titles’ words, which occur several times in articles cited in the analyzed collection, as the research trending topics. The longevity of the citation trend growth was the target for the machine learning algorithms. The CatBoost machine learning method, which is one of the best implementations of decision trees, was used. We conducted experiments on a scientific dataset that included 5 million publications from the top conferences in artificial intelligence and data mining areas to demonstrate the effectiveness of the proposed model. The accuracy rate of three-year forecasts for a number of experiments from 1997 to 2014 was about 60%. To visualize the forecast, the t-SNE and Word2Vec methods were used. Clusters of trending keywords on the semantic map helped to accurately identify promising directions. Two examples of forecast visualizations for the topic “Intelligent methods for data and image analysis” are presented. The presented visualizations serve as the analytical method for predicting topic trends and promising directions.

AKAida Khakimova
Aida Khakimova
XYXuejie Yang
Xuejie Yang
OZOleg Zolotarev
Oleg Zolotarev
MBMaria Berberova
Maria Berberova
MCMichael Charnine
Michael Charnine
The accelerating evolution of scientific terms connected with 4P-medicine terminology and a need to track this process has led to the development of new methods of analysis and visualization of unstructured information. We built a collection of terms especially extracted from the PubMed database. Statistical analysis showed the temporal dynamics of the formation of derivatives and significant collocations of medical terms. We proposed special linguistic constructs such as megatokens for combining cross-lingual terms into a common semantic field. To build a cyberspace of terms, we used modern visualization technologies. The proposed approaches can help solve the problem of structuring multilingual heterogeneous information. The purpose of the article is to identify trends in the development of terminology in 4P-medicine.

1 December 2015
Verified
Conference Paper
Closed access
MCMichael Charnine
Michael Charnine
SKStanislav Klimenko
Stanislav Klimenko
Traditional bibliometrics such as citation counts and Science Citation Index are often used to find most influential and quality scientific articles. Modern methods of analysis of citation graph take into account the content of the articles. Topical influence measures a tendency of an article to influence the ideas of citing articles. The presented method estimates the information content and ideas of scientific articles based on linguistic approach. The method can measure \"idea-based\" influence and how ideas propagate between articles. Idea is presented very precisely as a set of phrases with similar meaning. Phrases representing the ideas in the texts of the articles form together a system of implicit references/links. Implicit link is a reference to the author or his ideas in the text. Bibliometric indicators which in addition to bibliographic references also take into account the implicit links can more accurately measure scientific impact and the quality of the articles.

17 December 2020
Verified
Journal Article
Open access
AKAida Khakimova
Aida Khakimova
DGDongxiao Gu
Dongxiao Gu
OZOleg Zolotarev
Oleg Zolotarev
MBMaria Berberova
Maria Berberova
MCMichael Charnine
Michael Charnine
Due to the increasing popularity of new research in medicine thisstudy was conducted to determine recent research trends of predictive, preventive and personalized medicine (PPM). We identified the terms relevant to PPM using own search engine based on neural network processing in PubMed database. We extracted initially about 15000 articles. Then we carried out the statistical analysis for identifying research trends. The article presents the results of solving the problem of evaluating research topics at the level of thematic clusters in a separate subject area. An approach based on the analysis of article titles has been implemented. Identification of terms, connections between them and thematic clustering were carried out using the free software VOSViewer, which allows to extract terms in the form of noun phrases, as well as to cluster them.

14 August 2024 in SibScript
Verified
Journal Article
Open access
PDF file
MCMichael Charnine
Michael Charnine
СКСтепан Сергеевич Калинин
Степан Сергеевич Калинин
МШМихаил Михайлович Шарнин
Михаил Михайлович Шарнин
Natural language processing methods can be used to predict advanced application trends in formal ontologies. Formal ontologies help to formalize the characteristics of objects in various domains. As a result, machine learning programs identify patterns and relationships between these characteristics. The article describes an experiment based on machine learning methods in combination with text search methods. It involves the CatBoost algorithm for predictive modeling and clustering of lexical items. The vector models of the corresponding items reflect a trend in a particular domain of knowledge; proximity between them was calculated based on the idea of semantic distance. The experiment revealed four advanced areas for formal ontologies, i.e., genotype – phenotype; personalization; clustering algorithms, and collaborative task management. Each area that represented the predictable trends of development in this particular domain was provided with keywords. The article also contains a review of most popular scientific articles on these trends.