Authors
- Bosenko Timur Murtazovich Candidate of Technical Sciences
Annotation
Modern approaches to teaching big data analytics and machine learning require the integration of multimodal technologies, which allows students to develop skills in working with heterogeneous information sources, such as text, numeric, multimedia, and streaming data. The objective of the study is to investigate machine learning methods, including streaming data processing using Apache Spark, to solve a real-world business problem within the framework of project-based learning. Evaluation of the effectiveness of various teamwork methods (project-based learning, cooperative learning, case learning) showed that the best results in model accuracy (AUC = 0.91) are achieved when applying an integrated approach using all multimodal technologies within the framework of project work. The article analyzes in detail the results obtained using technologies such as text data processing (NLP), streaming data, numeric and multimedia data. The use of these technologies has significantly increased the accuracy of customer churn predictions, improved business decision-making, and developed students’ practical skills in big data analytics and artificial intelligence.
How to link insert
Bosenko, T. M. (2025). INTEGRATION OF MULTIMODAL TECHNOLOGIES INTO THE EDUCATIONAL PROCESS ON THE EXAMPLE OF DEVELOPING MACHINE LEARNING MODEL ON THE APACHE SPARK PLATFORM Bulletin of the Moscow City Pedagogical University. Series "Pedagogy and Psychology", № 1 (71), 80. https://doi.org/10.24412/2072-9014-2025-171-80-89
References
1.
1. Sahoo C. Sentiment analysis using deep learning techniques: a comprehensive review / C. Sahoo, M. Wankhade, B. K. Singh // International Journal of Multimedia Information Retrieval. 2023. Vol. 12. No. 2. P. 41. DOI: 10.1007/s13735-023-00308-2
2.
2. Simonov V. S. Method of imperative code transformation for parallel data processing platforms / V. S. Simonov, M. S. Khayretdinov // Problems of computer Science. 2023. No. 3 (60). P. 68–80. DOI: 10.24412/2073-0667-2023-3-68-80
3.
3. Bosenko T. M. Tools for collecting, storing and transmitting big data in infocommunication systems: a textbook / T. M. Bosenko. Moscow: Editus, 2023. 68 p.
4.
4. Benymol J. Enhanced query performance for stored streaming data through structured streaming within spark SQL / J. Benymol, R. Nithin, J. Lumy // Indonesian Journal of Electrical Engineering and Computer Science. 2024. Vol. 35. No. 3. P. 1744–1750. DOI: 10.11591/ijeecs.v35.i3.pp1744-1750
5.
5. Sadykova R. H. Storytelling as a neuro-linguistic didactic method in teaching (practice-oriented approach) / R. H. Sadykova, M. T. Kordzadze // Pedagogical Journal. 2023. Vol. 13. No. 12-1. P. 176–190. DOI: 10.34670/AR.2024.20.99.020
6.
6. Shunina L. A. The use of cloud technologies in the organization of industrial practice of students of a pedagogical university / L. A. Shunina // MCU of Journal of Informatics and Informatization of Education. 2022. No. 2 (60). P. 18–29. DOI: 10.25688/2072-9014.2022.60.2.02
7.
7. Bosenko T. M. The use of OLAP technology in the process of teaching students of specialty 03/38/05 — business informatics / T. M. Bosenko, P. K. Grigoriev // Actual problems of theory and practice of teaching physico-mathematical and technical disciplines in the modern educational space: Collection of selected articles of the VI All-Russian (with international participation) Scientific and Practical Conference (Kursk, December 15–16, 2022). Kursk: Kursk State University, 2022. P. 146–150.
8.
8. Gorbacheva E. A. The effectiveness of the development of information competence in the application of the project approach in the study of humanities in higher education / E. A. Gorbacheva // MCU of Journal of Informatics and Informatization of Education. 2024. No. 3 (69). P. 91–100. DOI: 10.25688/2072-9014.2024.69.3.8
9.
9. Tropnikova V. V. Using the eduscrum method: problems and solutions / V. V. Tropnikova // Secondary vocational education. 2021. No. 12 (316). P. 3–5.
10. Jordan M. I. Machine learning: Trends, perspectives, and prospects / M. I. Jordan, T. M. Mitchell / Science. 2015. Vol. 349. No. 6245. P. 255–260. DOI: 10.1126/science.aaa8415
10.
11. Hossin M. A Review on Evaluation Metrics for Data Classification Evaluations / M. Hossin, M. A. Sulaiman // International Journal of Data Mining & Knowledge Management Process. 2015. Vol. 5. No. 2. P. 1–11. DOI: 10.5121/ijdkp.2015.5201
11.
12. Malchevskaya P. A. Forecasting customer outflow based on a machine learning model / P. A. Malchevskaya // League of Researchers of Moscow State Pedagogical University: Collection of materials of the student open conference. In 2 parts (Moscow, November 20–24, 2023). Moscow: Moscow City University, 2024. P. 116–119.
12.
13. Frolov Yu. V. AI/ML data platforms based on domestic software / Yu. V. Frolov, T. M. Bosenko, D. V. Yatsenko // Modern {digital} didactics. Moscow: A-Prior, 2023. P. 119–128.
13.