Anton Kolotusha

Dr. Anton Kolotusha

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
13 February 2024 in Mathematics
Verified
Journal Article
Open access
PDF file
IKIrina Kalabikhina
Irina Kalabikhina
Vadim MoshkinVadim Moshkin
Vadim Moshkin
AKAnton Kolotusha
Anton Kolotusha
MKMaksim Kashin
Maksim Kashin
GKGerman Klimenko
German Klimenko
Zarina KazbekovaZarina Kazbekova
Zarina Kazbekova
Currently, direct surveys are used less and less to assess satisfaction with the quality of user services. One of the most effective methods to solve this problem is to extract user attitudes from social media texts using natural language text mining. This approach helps to obtain more objective results by increasing the representativeness and independence of the sample of service consumers being studied. The purpose of this article is to improve existing methods and test a method for classifying Russian-language text reviews of patients about the work of medical institutions and doctors, extracted from social media resources. The authors developed a hybrid method for classifying text reviews about the work of medical institutions and tested machine learning methods using various neural network architectures (GRU, LSTM, CNN) to achieve this goal. More than 60,000 reviews posted by patients on the two most popular doctor review sites in Russia were analysed. Main results: (1) the developed classification algorithm is highly efficient—the best result was shown by the GRU-based architecture (val_accuracy = 0.9271); (2) the application of the method of searching for named entities to text messages after their division made it possible to increase the classification efficiency for each of the classifiers based on the use of artificial neural networks. This study has scientific novelty and practical significance in the field of social and demographic research. To improve the quality of classification, in the future, it is planned to expand the semantic division of the review by object of appeal and sentiment and take into account the resulting fragments separately from each other.

28 April 2021 in Mathematics
Verified
Journal Article
Open access
PDF file
IKIrina Evgenievna Kalabikhina
Irina Evgenievna Kalabikhina
EBEVGENY BANIN
EVGENY BANIN
IAImiliya Abduselimovna Abduselimova
Imiliya Abduselimovna Abduselimova
GKGerman Klimenko
German Klimenko
AKAnton Kolotusha
Anton Kolotusha
Social networks have a huge potential for the reflection of public opinion, values, and attitudes. In this study, the presented approach can allow to continuously measure how cold “the demographic temperature” is based on data taken from the Russian social network VKontakte. This is the first attempt to analyze the sentiment of Russian-language comments on social networks to determine the demographic temperature (ratio of positive and negative comments) in certain socio-demographic groups of social network users. The authors use generated data from the comments to posts from 314 pro-natalist groups (with child-born reproductive attitudes) and eight anti-natalist groups (with child-free reproductive attitudes) on the demographic topic, which have 9 million of users from all over Russia. The algorithm of the sentiment analysis for demographic tasks is presented in the article. In particularly, it was found that comments under posts are more suitable for analyzing the sentiment of statements than the texts of posts. Using the available data in two types of groups since 2014, we find an asynchronous structural shift in comments of the corpuses of pro-natalist and anti-natalist thematic groups. Interpretations of the evidences are offered in the discussion part of the article. An additional result of our work is two open Russian-language datasets of comments on social networks.

28 December 2020 in Journal of Applied Informatics
Verified
Journal Article
Open access
LULomonosov Moscow State University
Lomonosov Moscow State University
IKIrina E. Kalabikhina
Irina E. Kalabikhina
VAVladimir N. Arkhangelsky
Vladimir N. Arkhangelsky
UNUliana G. Nikolaeva
Uliana G. Nikolaeva
AKAnton Kolotusha
Anton Kolotusha
IAImiliya A. Abduselimova
Imiliya A. Abduselimova
Demographic indicators are important functions of state programs for the development of Russia, operational monitoring of demographic development is the key to the successful implementation of programs. Very often, government statistics data are published with a delay, which does not allow their use for operational monitoring and planning. In this work, the approach allows for the rapid assessment of demographic processes in the field of formation and forecasting of demographic trends in the short term based on data from query statistics from Google Trends. The relationships between the search queries and demographics are analyzed using Pearson's correlation. The analysis uses annual (total fertility rate, abortions per 100 births, abortions per 1000 women, marriages and divorces per 1000 population) and monthly data (number of births, number of marriages and divorces) by birth, marriages and abortions with and without lags. The analysis is carried out on data for Russia as a whole and for the eight most populated regions: Moscow, Moscow Region, Krasnodar Territory, St. Petersburg, Rostov Region, Sverdlovsk Region, Republic of Tatarstan, Republic of Bashkortostan. Using the temporal metrics available in Google Trends since 2004, some demographics can be predicted based on data from related queries to the Google search algorithm using the ARIMA model. Thus, it is possible to use query data as a supplement to demographic data, when building multiple regression models for demographic calculations, or use it as a proxy variable.

5 September 2022 in Voprosy statistiki
Verified
Journal Article
Closed access
PDF file
OKO. V. Kuchmaeva
O. V. Kuchmaeva
NKN. M. Kalmykova
N. M. Kalmykova
AKAnton Kolotusha
Anton Kolotusha
The study aims to substantiate statistical and methodological approaches that allow the most accurate measurement of the contribution of the COVID-19 pandemic to the level and dynamics of the total mortality in the Russian Federation (in 2019–2020), and to assess the regional differentiation of mortality from the pandemic. The relevance of the study stems from revealing the role of some factors in the rise of mortality rates in Russia (according to data for 2020).In the study, the authors used regression analysis with a set of factors determining pandemic-induced differences in changes in mortality rates across regions of the Russian Federation as a basic analytical tool. The information base of the study is a set of official statistics data, as well as regional representative results of sample socio-demographic surveys of Rosstat.The authors used a set of regression models to test the hypotheses about the influence of a combination of demographic and socioeconomic factors on the increase in the total mortality rate. A repeating set of factors affecting the increase in mortality in different models may indicate the stability of the influence of the following factors: the share of people employed in the service sector, migration turnover, the presence in a region of a city of 500 thou. inhabitants or more, and the death rate from COVID-19. The set of factors influencing the increase in mortality differs by type of settlement and by gender.The article argues for the possibility of using the crude mortality rate as a dependent variable in assessing the causes of mortality growth. A significant part of the regional variation in the increase in the total mortality rate in 2020 in Russian regions is explained by the characteristics of the demographic structure of the region (the share of elderly, the size of the household, the share of people with cancer), as well as the high population density and frequency of social contacts (especially in cities). Rise of COVID-19 related mortality rate had impact on the increase of the total urban mortality rate but did not lead to any significant growth in rural mortality rate.The problem of the need to improve the information base for the selection of objective indicators and methods for analyzing the contribution of the COVID-19 epidemic to the level and dynamics of mortality is emphasized. An important methodological conclusion relevant for further research is the need to search for instrumental variables for COVID-19 related mortality indicators, due to the correlation of factors with the total mortality rate and with the mortality rate from COVID-19, as well as the need for further analysis of changes in the national health care system and its funding amid the pandemic.

16 September 2025 in Population and Economics
Verified
Journal Article
Open access
PDF file
IKIrina E. Kalabikhina
Irina E. Kalabikhina
AKAnton Kolotusha
Anton Kolotusha
This database contains 18.492 negative patient reviews (rated one star out of five, where five is the highest level of medical service quality) from the Russian medical review aggregator infodoctor.ru, collected between July 2012 and August 2023. The database is presented in .xlsx format (UTF-8 encoding). The dataset covers 16 major Russian cities, including Moscow (8.108 reviews), St. Petersburg (2.356), and 14 other cities with a population of over a million (8.028). Reflecting dissatisfaction with the quality of medical services, this dataset provides important information about the problems in the healthcare delivery across regions and socio-demographic groups. The data are presented as full-text reviews, which allows for an in-depth analysis of patient experience using text content analysis. Structured variables such as city, date, complaint type, doctor’s specialty, patient’s gender also allow for quantitative analysis using econometric methods. The combination of methods allows us to gain insight into patient dissatisfaction with medical services in Russian cities with a population of over a million for more than a decade.

20 October 2025 in Healthcare
Verified
Journal Article
Open access
PDF file
IKIrina Evgenievna Kalabikhina
Irina Evgenievna Kalabikhina
AKAnton Kolotusha
Anton Kolotusha
Vadim MoshkinVadim Moshkin
Vadim Moshkin
Background: The growth of digital patient feedback presents a new opportunity for healthcare quality monitoring. This study addresses the need to automatically classify the content of patient reviews to identify primary sources of dissatisfaction. Objective: The purpose of this study is to develop a machine learning algorithm for classifying negative patient reviews into two core categories: medical content (M—pertaining to diagnosis, treatment, and outcomes) and organizational support (O—pertaining to logistics, cost, and communication). We aim to identify which type of concern prevails and to analyze variations across cities, patient gender, and medical specialties. Methods: A database of 18,680 negative patient reviews (rated 1 star) was compiled from the Russian aggregator infodoctor.ru for the period from July 2012 to August 2023. A training set was created using an independent annotation procedure with three experts. A logistic regression model was trained to classify reviews into M and O categories, demonstrating an accuracy of 88.5%. Results: The analysis revealed a significant structural shift in Moscow, where since 2021, medical (M) complaints began to prevail over organizational (O) ones. This trend was not observed in St. Petersburg or other major Russian cities. Notably, in St. Petersburg, M-type reviews were more common within the most represented medical specialties, whereas O-type reviews consistently dominated in other cities. Gender differences were most pronounced in St. Petersburg, where women were more frequently authors of M reviews and men of O reviews. Conclusions: The developed algorithm provides a valuable tool for the automated monitoring of patient feedback. It enables healthcare managers to distinguish between clinical and service-related issues, facilitating targeted improvements in medical service quality and patient satisfaction.