?
Types of Dropout in Adaptive Open Online Courses
P. 273–279.
Skryabin M.
This study is devoted to different types of students’ behavior before they drop an adaptive course. The Adaptive Python course at the Stepik educational platform was selected as the case for this study. Student behavior was measured by the following variables: number of attempts for the last lesson, last three lessons solving rate, the logarithm of normed solving time, the percentage of easy and difficult lessons, the number of passed lessons, and total solving time. We applied a standard clustering technique, K-means, to identify student behavior patterns. To determine optimal number of clusters, the silhouette metrics was used. As the result, three types of dropout were identified: “solved lessons”, “evaluated lessons as hard’’, and “evaluated lessons as easy”.
In book
Vol. 10254: Digital Education: Out to the World and Back to the Campus. , Springer, 2017.
Porosenkov G., Цепелевич М. М., Кизяков Д. А. et al., Информатика и образование 2025 Т. 40 № 2 С. 57–65
Research on learner engagement in massive open online courses (MOOCs) has predominantly focused on those developed by educational and non-profit organizations. However, the significance of MOOCs offered by IT service providers (vendors), particularly in the field of cloud computing, has gained prominence in recent years. These vendor-led courses facilitate interaction between learners and vendors, underscoring the ...
Added: January 18, 2026
Rubchinskiy A., Chubarova D., Technology and Investment 2025 Vol. 16 No. 4 P. 211–240
The article considers one of the most famous examples of socio-economic systems characterized by significant uncertainty—the S&P-500 stock market, where shares of 500 largest US companies are traded. The flexible algorithm for daily trading has been developed. It is based on known fixed data about cost of shares in previous days as well as on ...
Added: December 19, 2025
Бояров Е. Н., Абрамова С. В., Купцова О. В. et al., Педагогика. Вопросы теории и практики 2025 Т. 10 № 5 С. 588–599
The aim of this research is to theoretically substantiate the possibility of applying a neural network approach to constructing a modern educational process in higher education. The article examines the main machine learning methods used for analyzing educational data and justifies the necessity of their implementation into the educational process. Particular attention is paid to ...
Added: December 9, 2025
Minaeva E., Zakharova U., Zhuchkova S., , in: Digital Education: Shaping Sustainable Lifelong Learning for All in the Era of AI. 9th European MOOCs Stakeholders Summit, EMOOCs 2025, Paris, France, June 30 – July 2, 2025, Proceedings.: Springer, 2026. P. 130–143.
One of the promises of MOOC platforms that were widely discussed during the first two waves of MOOC popularity in 2010–2016 was its marketing potential for international student recruitment. However, the research on the effects of MOOC on international enrolment is currently scarce. Based on the data from Coursera and edX platforms for MOOC supply ...
Added: October 1, 2025
Stepanov M., Slastnikov S., Климин Н. А., Программные системы: теория и приложения 2025 Т. 16 № 4 С. 3–21
Modern educational systems accumulate large volumes of data on students' digital activity across various information systems, yet the effective utilization of this data for education personalization remains an unresolved challenge. The formation of a student's digital profile allows for systematizing disparate data and using it to support pedagogical decisions.
The article presents a model for digital ...
Added: June 11, 2025
The Video Lecture as an Instructional Method of MOOCS: Impact on the Students' Re-Watching Behaviors
Shittu M., Gorbunova A., Lange C. et al., Electronic Journal of e-Learning 2025 Vol. 23 No. 2 P. 64–79
This study examines the relationship between instructional delivery that affects students' engagement with video lectures and the need to re-watch video lectures in the context of Massive Open Online Courses (MOOCs), where video lectures are the predominant mode of instruction. Multiple linear regression was used to investigate the relationships between some key characteristics of video ...
Added: June 5, 2025
F. T. Aleskerov, A. L. Myachin, V. I. Yakuba, Doklady Mathematics 2024 Vol. 110 No. 3 P. 474–479
We propose a novel method for rapid pattern analysis of high-dimensional numerical data, termed tunnel clustering. The main advantages of the method are its relatively low computational complexity, endogenous determination of cluster composition and number, and a high degree of interpretability of final results. We present descriptions of three different variations: one with fixed hyperparameters, ...
Added: March 3, 2025
Гусейнов О., Degtyarev K. Y., IRETC MTÜ PAHTEI - Proceedings of Azerbaijan High Technical Educational Institutions 2025 Т. 48 № 1 С. 360–370
The concept of Z-number was proposed by Prof. Lotfi Zadeh to describe partial reliability of information, and it is a kind of fusion of fuzziness and probabilistic uncertainty. Z-number can be presented as a pair of fuzzy numbers Z(A,B) used to describe a value of a random variable X. The first component (A) is a ...
Added: February 20, 2025
Al Murshidi G., Adamovich K., Costley J. et al., International Journal of Distance Education Technologies 2025 Vol. 23 No. 1 P. 1–14
The aim of the present paper is to explore students' perceptions of MOOCs in relation to their learning strategies. Drawing upon cognitive appraisal theory and learning strategies framework, the study examines the perception of MOOCs as threats or challenges and assesses students' learning approaches through the prism of deep and surface learning strategies. Survey data ...
Added: February 16, 2025
Shalileh S., Social Network Analysis and Mining 2025 Vol. 15212 P. 137–148
Community detection in attributed networks aims to recover clusters in which the within-community nodes are as interconnected and as homogeneous as possible, while the between-communities nodes are as disconnected and as heterogeneous as possible. The current research proposes a straightforward data-driven model with an integrated regularization term to recover communities. For further improvement of the ...
Added: November 30, 2024
T. A. Alvandyan, S. Shalileh, Doklady Mathematics 2024 Vol. 110 No. S1 P. S236–S250
Clustering has always been in great demand by scientific and industrial communities. However, due to the lack of ground truth, interpreting its obtained results can be debatable. The current research provides an empirical benchmark on the efficiency of three popular and one recently proposed crisp clustering methods. To this end, we extensively analyzed these (four) ...
Added: November 30, 2024
Богданова Т. К., Жукова Л. В., В кн.: XI-я международная конференция «Многомерный статистический анализ, эконометрика и моделирование реальных процессов» имени С.А. Айвазяна.: М.: ЦЭМИ РАН, 2024. С. 41–44.
The paper is devoted to the analysis and forecasting of the average salary of teachers. For 84 regions on the basis of their socio-demographic characteristics according to Rosstat data using Ward's method we obtained a two-cluster solution, which allowed us to identify quite strong differences in the level of wages, GRP per capita, level of ...
Added: October 4, 2024
Penikas H. I., Феста Ю. Ю., Известия Дальневосточного федерального университета. Экономика и управление 2024 Vol. 2 P. 75–94
Кластерный анализ широко используется в различных научных и практических областях, связанных с анализом данных. Это важный инструмент для решения задач в таких областях, как машинное обучение, обработка изображений, распознавание текста и т.д. Отсутствие наблюдений не всегда означает отсутствие информации, поэтому предполагается, что наличие пробелов в данных, наличие“пустых” кластеров, также несёт в себе информацию об объекте исследования, как и реальные наблюдения. В этом исследовании предполагается, ...
Added: August 10, 2024
Koile E., Moroz G., Journal of Linguistic Geography 2024 Vol. 12 No. 1 P. 24–31
Geolectal variation is often present in settings where one language is spoken across a vast geographic area. This can be found in phonological, morphosyntactic, and lexical features. For practical reasons, it is not always possible to conduct fieldwork in every single location of interest in order to obtain the full pattern of variation, and a ...
Added: May 6, 2024
Gromov V., Dang Q. N., , in: 10th International Conference, PReMI 2023, Kolkata, India, December 12–15, 2023, Proceedings. Pattern Recognition and Machine Intelligence. LNCS, volume 14301.: Cham: Springer, 2023. Ch. 3 P. 20–27.
Added: November 29, 2023
Backs A., Al-Falou A., Vagov A. et al., Physical Review B: Condensed Matter and Materials Physics 2023 Vol. 107 No. 17 Article 174527
In the vicinity of the type-I/type-II crossover in conventional superconductors, vortices exhibit a nonmonotonic interaction, which leads to exotic vortex matter states. We perform molecular dynamics simulations on a model superconductor in the intertype regime. In a field cooled approach, we examine the transition of a homogeneous vortex lattice (VL) into a structure consisting of ...
Added: November 2, 2023
Alshanskaia E., Martynova O., IEEE, 2023.
Cognitive and emotional load in the course of increasing the complexity of tasks leads to the activation of various parts of the autonomic nervous system (ANS) and can be accompanied by an increase in the efficiency of problem solving. An increase in cognitive load under the condition of high motivation is a stress factor and ...
Added: September 24, 2023
Beklaryan A., Вестник ЦЭМИ 2023 Т. 6 № 1 Статья 5
The article presents a new software platform for modelling traffic flows involving unmanned vehicles, using a number of advanced technological solutions, in particular, the FLAME GPU supercomputer agent modelling framework, intelligent software modules based on fuzzy and hierarchical clustering, genetic optimization algorithms, a subsystem for visualizing the state of agents-vehicles based on OpenGL, etc. As ...
Added: June 4, 2023
A. Vagov, E. G. Nikonov, The Journal of Physical Chemistry Letters 2023 Vol. 14 No. 15 P. 3743–3748
By investigating spatial configurations of the intermediate mixed state in an intertype superconductor, it is shown that vortex clustering can be characterized by the sample averaged distribution of the penetrating magnetic field. The clustering is manifested in the two peak structure of the distribution. The second peak indicates a spot a material occupies in the ...
Added: June 2, 2023