Big data technologies in e-learning

Recently, e-learning around the world is rapidly developing, and the main problem is to provide the students with quality educational information on time. This task cannot be solved without analyzing the large flow of information, entering the information environment of e-learning from participants in the educational process – students, lecturers, administration, etc. In this environment, there are a large number of different types of data, both structured and unstructured. Data processing is difficult to implement by traditional statistical methods. The aim of the study is to show that for the development and implementation of successful e-learning systems, it is necessary to use new technologies that would allow storing and processing large data streams.

In order to store the big data, a large amount of disk space is required. It is shown that to solve this problem it is efficient to use clustered NAS (Network Area Storage) technology, which allows storing information of educational institutions on NAS servers and sharing them with Internet. To process and personalize the Big Data in the environment of e-learning, it is proposed to use the technologies MapReduce, Hadoop, NoSQL and others. The article gives examples of the use of these technologies in the cloud environment. These technologies in e-learning allow achieving flexibility, scalability, availability, quality of service, security, confidentiality and ease of educational information use.

Another important problem of e-learning is the identification of new, sometimes hidden, interconnection in Big Data, new knowledge (data mining), which can be used to improve the educational process and improve its management. To classify electronic educational resources, identify patterns of students with similar psychological, behavioral and intellectual characteristics, developing individualized educational programs, it is proposed to use methods of analysis of Big Data.

The article shows that at present many software applications have been developed for the intellectual analysis of Big Data. These software products can be used for classification, clustering, regression and network analysis of training information. The application of these methods in e-learning will allow lecturers to receive timely information about students, promptly respond to any changes in the learning process, and timely make changes to educational content. The results of the research are proposed to be used to develop recommendations for the creation of electronic courses in higher and secondary educational institutions of Azerbaijan. 

1. URL: www.sloan.com

2. Belaya kniga «Elektronnoe obuchenie v Rossii». Ed. N.V. Tikhomirovoy, M.: Minobrnauki, 2014. P.137 (In Russ.)

3. Pat Nakamoto. BIG DATA: The revolution that is transforming our work, market and world. Data Analysis / Kindle Edition, 2013. P. 212.

4. Franks B., Taming the big data tidal wave. John Wiley & Sons, Inc. 2010. P. 341.

5. Mayer-Shenberger V., Kuk’er K. Bol’shie dannye. Revolyutsiya, kotoraya izmenit to, kak my zhivem, rabotaem i myslim. Moscow: Izdatel’stvo «Mann, Ivanov i Ferber», 2014. P. 208.

6. Badarch Dendev. Informatsionnye i kommunikatsionnye tekhnologii v obrazovanii. Moscow: IITO YuNESKO, 2013. P. 320.

7. Ian H. Witten, Eibe Frank. Data Mining: Practical machine learning tools and techniques. “Morgan Kaufmann”, 2015. P. 229.

8. Baker, R. S. Educational data mining: An advance for intelligent systems in education. IEEE Intelligent Systems, 2014. 29 (3). P. 78-82.

9. Bishop Ch. Pattern Recognition and Machine Learning. Series: Information Science and Statistics. 2006. T. XX. 740 p.

10. Dyuk V.A., Samoylenko A.P. Data Mining: uchebnyy kurs. Saint Petersburg: Piter, 2001. P. 312. (In Russ.)

11. Erdos P., Renyi A. On the evolution of random graphs. Publication of Mathematics Institute Hungary Academy of the Science. 1960. V. 5. P. 17-61.

12. Wellman, B. The community question. American Journal of Sociology, 1979, 84, p. 1201- 1207.

13. J. Ross Quinlan: Decision Trees and Instance-Based Classifiers. The Computer Science and Engineering Handbook, 1997. P. 521-535.

14. Zaytseva T. Pusnaya O. Veroyatnostnye derev’ya resheniy: Programmnaya realizatsiya v reshenii zadach klassifikatsii i prognozirovaniya. Lambert Academic Publisher, 2014. P. 96 (In Russ.)

15. URL: https://myspace.com

16. Ferguson, R. (2012). Learning analytics: Drivers, developments and challenges. International Journal of Technology Enhanced Learning. 4(5/6). P. 304-317.

17. Asha T, Shravanthi U.M, Nagashree N, Monika M, Building Machine Learning Algorithms on Hadoop for Bigdata. International Journal of Engineering and Technology. 2013. Vol. 3. No. 2. P. 143-147.

18. Qi Zhang, Lu Cheng, and Raouf Boutaba. Cloud computing: stateof-the-art and research challenges. Journal of Internet Services and Applications. 1(1): 2010. P. 7-18

19. URL: www.storm.apache.org, URL: www. spark.apache.org.

20. J. Schmidhuber. Deep learning in neural networks: An overview. Neural Networks, 61: 2015. P. 85-117.