Çevrimiçi Öğrenme Ortamında Akademik Başarıyı Artırmak İçin Karar Destek Sistemi

Abstract

Karar desktek sistemleri(KDS) kurum ve organizasyonlar için geliştirilen, karar vericilerin daha sağlıklı ve gerekçeli kararlar almasını sağlayan sistemlerdir. Bu sistemler, çevirimiçi eğitim ortamlarında, özellikle daha yüksek başarı elde etmek için öğrenci ve eğitim yöneticilerinin kullanımına sunulmaktadır. Çevrimiçi öğrenme ortamlarında, öğrenciler farklı türlerde ders materyalleri ve etkileşim araçları kullanmaktadır. Fakat, çoğu zaman öğrenciler akademik performanslarını olumlu yönde etkileyecek ders içerikleri ve etkinliklerin seçiminde zorlanırlar.

Bu çalışmada, öğrencilere ve eğitim yöneticilerine etkinlik öneri karar destek modeli oluşturulmuştur. Model, öğrencilerin geçmiş verilerini işleyerek en iyi etkinlik seçimine yardımcı olur. Karar destek sisteminde, veri madenciliği yöntemi kullanılmıştır. veri ambarı için muhtemel özellikler ve veriler, moodle öğrenme yönetim sistemi (ÖYS) aracılığıyla elde edilmektedir. Daha sonra, modelin performansını artırmaya katkıda bulunan nitelikler, veri madenciliği işlemini uygulamak için filitrelendi. Veri madenciliği sürecinde geleceğe yönelik tahmin işlemleri için birçok karar ağacı algoritması kullanılmıştır. Ancak, C5 algorimasının diğer karar ağacı algoritmalarından daha iyi performans sergilediği görülmüştür.

Veri madenciliği işleyişine ek olarak, örneklemin demografik yapısı, haftalık başarı oranları ve ders kullanım sayıları gibi çeşitli istatistiksel bilgilerde performansı artırmak için modele eklenmiştir. Model için web tabanlı bir uygulama tasarlanmış ve uygulama bölümünde yer verilmiştir.

Keywords

• : Çevrimiçi Öğrenme,Veri Madenciliği

Activity Suggestion Decision Support System Design In Online Learning Environment

Abstract

Decision support systems is created for organizations to enable decision makers to have healthier and more reasonable actions. These systems are made available to students and administrators in online education environments, especially for higher success. In online learning environments, students utilize different types of course materials and interaction tools, which provides reaching a higher success rate in a considerable amount. However, students often difficult to choose course content and activities that will positively affect their academic performance. In this study, the decision support system model is constituted for students and lecturer in terms of online learning environments. The model helps students choose the best activity by processing their previous data. Data mining methods have been used in decision making process. Possible features and data for the data warehouse are obtained through moodle learning management system. Then, the attributes that contributed to improving the performance of the model were filtered to implement the data mining process. In the data mining process of the research, many decision tree algorithms have been used for success predictions. However, it has been seen that C5 algorithm performs better than other decision tree algorithms. In addition to the data mining process, demographic structure of the sample, weekly success rates and number of course document usage were added to the model to improve performance in various statistical information. A web based application has been designed for the model and is added in the application section.

Keywords

• Online Learning,Educational Data Mining,Classification Methods,Decision Tree Algorithms,C5 Decision Tree Algorithm

References

1. [1] Cao, J., & Xiong, L. Protein Sequence Classification with Improved Extreme Learning Machine Algorithms, BioMed Research International, (2014), 1-12.
2. [2] Kör, H., Çataloğlu, E., & Erbay, H. Uzaktan ve Örgün Eğitimin Öğrenci Başarısı Üzerine Etkisinin Araştırılması. Gaziantep University Journal of Social Sciences, 12(3) (2013), 267-279.
3. [3] Karaman, K., & Akgül, İ. İlkokul Öğrencileri İçin Web Tabanlı Değerler Eğitimi Uygulaması. Uşak Üniversitesi Sosyal Bilimler Dergisi, 8(3) (2015), 87-100.
4. [4] Benoit, G. Data mining. Annual Review of Information Science and Technology, 36(1) (2002).
5. [5] Oracle. Data Mining Concepts. URL https://docs.oracle.com/cd/B28359_01/datamine.111/b28129/process.htm#DMCON002 ,2018.
6. [6] Guruler H., Istanbullu, & A., Karahasan, M. A. New student performance analysing system using knowledge discovery. Computers & Education, 55(1) (2010), 247-254.
7. [7] Manyika J., Chui, M., Brown, B., Bughin, J., Dobbs, R., Roxburgh,C., & Byers, A. Big Data: The Next Frontier for Innovation, Competition, and Productivity, McKinsey Global Institute, 2011.
8. [8] Castro F., Vellido, A., Nebot, A., & Mugica, F. Applying Data Mining Techniques to e-Learning Problems. Studies in Computational Intelligence, 62(1) (2007), 183-221.

9. [9] Wanli, X., Rui, G., Eva, P., & Sean, G., Participation-based student final performance prediction model through interpretable Genetic Programming: Integrating learning analytics, educational data mining and theory, Computers in Human Behavior, 47 (2015), 168-181.
10. [10] Peña-Ayala A. Educational data mining: A survey and a data mining-based analysis of recent works. Expert Systems with Applications, 41(4) (2014), 1432-1462.
11. [11] Diaz, V. Cloud-Based Technologıes: Faculty Development, Support, And Implementatıon, Journal of Asynchronous Learning Networks, 15(1) (2011), 95-102.
12. [12] Horzum M. B. Interaction, Structure, Social Presence, and Satisfaction in Online Learning, Eurasia Journal of Mathematics, Science & Technology Education, 11(3) (2015), 505-512.
13. [13] Pala F. K., & Erdem, M. Öğretmen Adaylarının Çevrimiçi Tartışma Ortamlarına Yönelik Görüşleri, Turkish Online Journal of Qualitative Inquiry, 6(2) (2015), 24-47.
14. [14] Cristóbal, C.S. e-Learning as an Object of Study, Universities and Knowledge Society Journal, 7(2) (2010), 1-11.
15. [15] Moreno L., Gonzalez, C., Castilla, I., Gonzalez, E., & Sigut, J. Applying a constructivist and collaborative methodological approach in engineering education. Computers & Education, 49(3) (2007), 891-915.
16. [16] Cheung Christy, M.K., Lee, Matthew, K.O., Lee, & Zach, W.Y. Understanding the continuance intention of knowledgesharing in online communities of practice through the post-knowledge-sharing evaluation processes. Journal of the American Society for Information Science & Technology, 64(7) (2013), 1357-1374.
17. [17] Tseng F. C., & Kuo, F.Y. A. Study of social participation and knowledge sharing in the teachers’ online professional community of practice. Computers & Education. 72(1) (2014), 37-47.
18. [18] Yao C.Y., Tsai, C.C. & Fang, Y.C. Understanding social capital, team learning, members’ e-loyalty and knowledge sharing in virtual communities. Total Quality Management & Business Excellence. 26(6) (2015), 619–631.
19. [19] Ifenthaler, D. From Educational Data Mining To Automated Analysis Of Semantics, Applied Teaching and Learning Research. Retiered from http://documents.epfl.ch/groups /m/mo/mooc-admins/www/documents/Ifenthaler-LAW.pdf, 2014.
20. [20] Siemens G., & Baker, R. S. Learning analytics and educational data mining: towards communication and collaboration, 2nd international conference on learning analytics and knowledge, Vancouver, British Columbia, Canada, 252-254, 2012.
21. [21] Ghisoiue et al. Designing a DSS for Higher Education Management, Proceedings of CSEDU2009, Lisbon, Portugal, (2009), 335-340.
22. [22] Bresfelean, V. P., & Ghisoio N.(2010), Higher Education Decision Making and Decision Support Systems, Wseas Transactions On Advances In Engineering Education, 2(7) (2010), 43-52.
23. [23] Bienkowski M., Feng, M., & Means, B.(2012). Enhancing Teaching and Learning Through Educational Data Mining and Learning Analytics: An Issue Brief, U.S. Department of Education, Office of Educational Technology. Washington, D.C, 2012.
24. [24] Baker R., S., & Inventado, P.S. Educational Data Mining and Learning Analytics, Learning Analytics: From Research to Practice. Ed: White J.A. Larusson and White. B. New York : Springer Science+Business Media, 2014.
25. [25] Gunnarsson B. L., & Alterman, R. Predicting failure: A case study in coblogging, Computers in Human Behavior. 2nd international conference on learning analytics. Vancouver, 29 Nisan - 2 May, 2012, British Columbia, Canada, 263-266, 2012.
26. [26] Siemens G., & Baker, R. S. Learning analytics and educational data mining: towards communication and collaboration, 2nd international conference on learning analytics and knowledge, 29 April-2 May, Vancouver, British Columbia, Canada, 252-254, 2012.
27. [27] Harrell F. E. Regression Modeling Strategies: With Applications to Linear Models, Springer, 2001.
28. [28] North M., Data Mining for the Masses. A Global Text Project Book, 2012.
29. [29] Ali L., Asadi, M., Gašević,D., Jovanović, J., & Hatala, M. Factors Influencing Beliefs For Adoption of Alearning Analyticstool: An Empirical Study. Computers & Education, 62(1) (2013), 130-148.
30. [30] Greller W., & Drachsler, H.Translating Learning into Numbers: A Generic Framework for Learning Analytics, Educational Technology & Society, 15(3) (2012), 42-57.
31. [31] Sencer M., Toplum bilimlerinde yöntem, Beta Basım, İstanbul, 1989.
32. [32] Gay L. R. , Educational research: Competencies for analysis and application (3rd ed.). Columbus: OH: Merrill, 1987.