Application of educational data mining in subject learning at university

Abstract

Problem statement. Digital technologies are being actively incorporated into all educational processes, in particular so-called “end-to-end technologies”, which among others include big data as a management tool within educational systems. However, the described examples of practical use of educational data analysis not for university management, but for specific subject teaching are yet limited. The aim of the study is to determine how big data can be applied to verify gaps in knowledge and learning progress and to adjust the educational track accordingly in the context of a particular university course. Methodology . The study was conducted at PetrSU utilizing the PACT (Petrozavodsk Annotated Corpus of Texts). PACT is a database that is continuously updated with students' texts in German. The texts are reviewed by experts who mark errors and assign a grade for the work. All information about mistakes is collected in a shared database, the visualization of which is accessible in the teacher's personal account. The paper presents charts and tables from this database and determines to what extent they can be used to analyze the progress of a particular student, a certain academic group or an entire course in the acquisition of a foreign language. Results . The feasibility of big data collection in the form of students' work in progress has been confirmed, which can then be effectively applied in teaching. The PACT linguistic corpus allows, on one side, to track progress in mastering individual topics and, on the other side, to verify gaps in students' knowledge and to adjust teaching methods to meet the needs. Conclusion . Digitalization of education can and should develop in the direction of creating databases that include students' works on various subjects. The prospects for the use of such big data technologies in the subject teaching are immense, so this area, currently underdeveloped due to various reasons, certainly deserves more attention from all participants of the system - from the ordinary teachers to researchers and managers responsible for the digital transformation of education.

About the authors

Irina A. Kotiurova

Petrozavodsk State University

Author for correspondence.
Email: koturova@petrsu.ru
ORCID iD: 0000-0001-6766-0458
SPIN-code: 7400-4245

Candidate of Sciences in Philology, Associate Professor, Head of the Department of German and French Languages

33 Lenina St, Petrozavodsk, 185910, Russian Federation

References

  1. Uvarov AYu, Geibl E, Dvoretskaya IV, Zaslavskii IM, Karlov IA, Mertsalova TA, Sergomanov PA, Frumin ID. Difficulties and prospects of digital transformation of education. Moscow: HSE University; 2019. (In Russ.) https://doi.org/10.17323/978-5-7598-1990-5
  2. Utyomov VV, Gorev PM. Development of educational systems based on Big Data technology. Concept. 2018;6:449‒461. (In Russ.) https://doi.org/10.24422/MCITO.2018.6.14501
  3. Bystrova T, Larionova V, Sinitsyn E, Tolmachev A. Learning analytics in massive open online courses as a tool for predicting learner performance. Educational Studies. 2018;(4):139‒166. (In Russ.) https://doi.org/10.17323/1814-9545-2018-4-139-166
  4. Shirinkina EV. Methods of data mining and educational analytics. Modern Education. 2022;(1):51‒67. (In Russ.) https://doi.org/10.26456/2219-1453/2021.3.179-188
  5. Prusakova PV, Semyonkina IA. Application of educational data analytics to improve the quality of higher education. Prospects for the Development of Higher Education. 2023;(2):395‒400. (In Russ.)
  6. Kustitskaya TA, Noskov MV. Development of learning analytics in Russia. Informatization of Education and e-Learning Methodology: Digital Technologies in Education: Proceedings of the V International Scientific Conference, Krasnoyarsk, 21‒24 September 2021 (vol. 1). Krasnoyarsk; 2021. p. 273‒278. (In Russ.)
  7. Vilkova KA, Zakharova US. Learning analytics in conventional education: its role and outcomes. Journal University Management: Practice and Analysis, 2020;24(3):59‒76. (In Russ.) http://doi.org/10.15826/umpa.2020.03.026
  8. Pomian S, Belokon О. Forecast of the results of academic performance of university students based on Markov processes. Herald of Vyatka State University. 2020;(4):63–73. (In Russ.) http://doi.org/10.25730/VSU.7606.20.057
  9. Sverdlov MB. (ed.) Educational analytics: management of educational organisation and content creation based on data. Moscow: HSE University; 2021. (In Russ.)
  10. Barannikov KA, Suleymanov RS, Lesin SM, Kupriyanov RB. Learning analytics based on educational data mining methods as a way to improve the effectiveness of the education management system. Lomonosov Pedagogical Education Journal. 2020;20(2): 16–33. (In Russ.)
  11. Fiofanova OA. Big data analysis in the field of education: methodology and technologies. Moscow: Delo Publ.; 2020. (In Russ.)
  12. Krein U, Schiefner-Rohs M. Data in schools: (changing) practices and blind spots at a glance. Frontiers in Education. 2021;6:672666. http://doi.org/10.3389/feduc.2021.672666
  13. Hase A, Kahnbach L, Kuhl P, Lehr D. To use or not to use learning data: a survey study to explain German primary school teachers’ usage of data from digital learning platforms for purposes of individualization. Frontiers in Education. 2022;7. http://doi.org/10.3389/feduc.2022.920498
  14. Kotiurova IA, Shchegoleva LW. Learner corpus in German as a data source for education and science. Educational Studies. 2022;(4):322‒349. (In Russ.) http://doi.org/10.17323/1814-9545-2022-4-322-349
  15. Tikhomirova T, Malykh S, Kovas Yu. Individual differences in learning capabilities: opportunities and prospects of behavioral genetic research. Educational Studies. 2012; (4):186‒199. (In Russ.) https://doi.org/10.17323/1814-9545-2012-4-186-199

Copyright (c) 2024 Kotiurova I.A.

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

This website uses cookies

You consent to our cookies if you continue to use our website.

About Cookies