Öğrencilerin Akademik Performanslarını Makine Öğrenmesi Teknikleriyle Değerlendiren Çalışmaların İncelenmesi

Abstract

Makine öğrenmesi tekniklerinin eğitim teknolojilerine uyarlanması yaygın hale gelmektedir. Akademik başarı iyileştirme ve öngörü çalışmaları da bunların arasında yer almaktadır. Makine öğrenmesinin eğitimde kullanımı, öğrencilerin bireysel ihtiyaçlarını ve öğrenme stillerini daha iyi anlamak, eğitim sistemlerini daha verimli hale getirmek ve öğrenci başarısını artırmak için önemli bir potansiyele sahiptir. Bu potansiyellerden yola çıkarak bu çalışmada öğrencilerin akademik başarılarının önceden tahmin edilmesi veya sınıflandırılması incelenmiş, literatürdeki önde gelen modeller, yöntemler ve araçlar araştırılmıştır. Literatürde son 15 yılda gerçekleştirilen çalışmalar farklı veri tabanlarından indirilerek analiz edilmiş ve tüm boyutlarıyla irdelenmiştir. Çalışmalarda kullanılan algoritmalar, öznitelik seçim teknikleri, analiz araçları ve ölçüm metrikleri bakımından bulgular elde edilmiş ve istatistiki bilgilerle sunulmuştur. Özellikle, Yapay Sinir Ağları, Lojistik Regresyon, Çok Katmalı Algılayıcılar, Rastgele Orman ve K-En Yakın Komşu gibi algoritmaların yüksek başarı oranları elde ettiği gözlemlenmiştir. Literatürde en sık kullanılan öznitelik seçim tekniği Bilgi Kazancı (Information Gain-IG) olurken, en sık kullanılan sınıflandırma algoritması Naive Bayes olarak belirlenmiştir. En başarılı 10 modelin analizi, öznitelik seçim teknikleri ve sınıflandırma algoritmalarıyla birlikte sunulmuştur. Öğrenci performansını etkileyen temel faktörler arasında ebeveynlerin eğitim düzeyleri, öğrencinin daha önce aldığı eğitim kalitesi ve ailenin gelir düzeyi öne çıkmaktadır. Bu çalışma, literatüre kapsamlı bir analiz sunmakta olup, gelecek araştırmalar için bir başlangıç noktası olarak değerlendirilebilir.

Keywords

• Akademik başarı
• öğrenci performansı
• makine öğrenmesi
• öznitelik seçimi

A Review of Studies Evaluating Students' Academic Performance with Machine Learning Techniques

Abstract

The adaptation of machine learning techniques to educational technologies is becoming widespread. Academic achievement improvement and prediction studies are among them. The use of machine learning in education has significant potential to better understand students' individual needs and learning styles, to make educational systems more efficient and to increase student achievement. Based on these potentials, this study examines the prediction or classification of students' academic achievement and surveys the leading models, methods and tools in the literature. The studies conducted in the last 15 years in the literature were downloaded from different databases and analyzed and examined in all dimensions. Findings in terms of algorithms, feature selection techniques, analysis tools and measurement metrics used in the studies are obtained and presented with statistical information. In particular, algorithms such as Artificial Neural Networks, Logistic Regression, Multilayer Perceptrons, Random Forest and K-Nearest Neighbor have been observed to achieve high success rates. The most frequently used feature selection technique in the literature is Information Gain (IG), while the most frequently used classification algorithm is Naive Bayes. The analysis of the 10 most successful models is presented along with feature selection techniques and classification algorithms. The main factors affecting student performance are parents' level of education, the quality of the student's previous education, and family income level. This study provides a comprehensive analysis to the literature and can be considered as a starting point for future research.

Keywords

• Academic achievement
• student performance
• machine learning
• attribute selection
• assessment

References

1. [1] B. Aslan and M. C. Babadoğan, “Relationships between learning style preferences and gender, age and success level at 7th and 8th Grade,” Eurasian Journal of Educational Research, vol. 21, pp. 35-48, 2005.
2. [2] R. R. F. Mendes, F. B. de Voznika, A. A. Freitas, and J. C. Nievola, “Discovering Fuzzy Classification Rules with Genetic Programming and Co-evolution,” in Principles of Data Mining and Knowledge Discovery, L. De Raedt ve A. Siebes, Ed., Berlin, Heidelberg: Springer Berlin Heidelberg, pp. 314-325, 2001.
3. [3] M. Ünver, E. Erdal, and A. Ergüzen, “Big Data Example In Web Based Learning Management Systems,” International Journal of Advanced Computational Engineering and Networking, vol. 6, no. 2, pp. 39-42, 2018.
4. [4] S. Buyrukoğlu, “A novel color labeled student modeling approach using e-learning activities for data mining,” Univers Access Inf Soc, vol. 22, no. 2, pp. 569-579, June 2023. doi:10.1007/S10209-022-00894-8/TABLES/7
5. [5] A. Peña-Ayala, “Educational data mining: A survey and a data mining-based analysis of recent works,” Expert Syst Appl, vol. 41, no. 4, pp. 1432-1462, March 2014. doi:10.1016/J.ESWA.2013.08.042
6. [6] B. G. Emiroglu and S. Sahin, “Analysis of Students’ Performances during Lab Sessions of Computer Networks Course,” J Educ Techno Soc, vol. 16, no. 3, pp. 329-346, 2013.
7. [7] R. Bütüner and M. H. Calp, “Estimation of the Academic Performance of Students in Distance Education Using Data Mining Methods,” International Journal of Assessment Tools in Education, vol. 9, no. 2, pp. 410-429, June 2022. doi:10.21449/IJATE.904456
8. [8] S. Kayalı and S. Buyrukoğlu, “Makine Öğrenmesi Yöntemleriyle Öğrencilerin Akademik Performanslarının Sınıflandırılması,” in 2nd International Conference On Educational Technology And Online Learning-ICETOL, pp. 330, 2022

9. [9] S. Buyrukoglu, F. Batmaz, and R. Lock, “Semi-Automatic Assessment Approach to Programming Code for Novice Students,” in Proceedings of the 8th International Conference on Computer Supported Education (CSEDU 2016), pp. 289-297, 2016
10. [10] İ. Yücedağ and O. Güler, “Fuzzy Logic Based Approach to Site Selection Problem of Vocational Secondary School Students,” Hacettepe University Journal of Education, vol. 32, no. 1, pp. 111-122, 2017.
11. [11] S. Agarwal, G. N. Pandey, and M. D. Tiwari, “Data Mining in Education: Data Classification and Decision Tree Approach,” International Journal of e-Education, e-Business, e-Management and e-Learning, vol. 2, no. 2, pp. 140-144, 2012. doi:10.7763/IJEEEE.2012.V2.97
12. [12] T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning. in Springer Series in Statistics. New York, NY: Springer New York, 2009. doi:10.1007/978-0-387-84858-7
13. [13] E. Alyahyan and D. Düştegör, “Predicting academic success in higher education: literature review and best practices,” International Journal of Educational Technology in Higher Education, vol. 17, no. 1, pp. 1-21, December 2020. doi:10.1186/S41239-020-0177-7/TABLES/15
14. [14] A. Hellas et al., “Predicting academic performance: A systematic literature review”, in Annual Conference on Innovation and Technology in Computer Science Education, ITiCSE, Association for Computing Machinery, pp. 175-199, July 2018. doi:10.1145/3293881.3295783
15. [15] B. Albreiki, N. Zaki, and H. Alashwal, “A Systematic Literature Review of Student’ Performance Prediction Using Machine Learning Techniques”, Educ Sci (Basel), vol. 11, no. 9, 2021. doi:10.3390/educsci11090552
16. [16] S. Savaş and S. Karataş, “Cyber governance studies in ensuring cybersecurity: an overview of cybersecurity governance,” International Cybersecurity Law Review, vol. 3, pp. 7-34, 2022. doi:10.1365/s43439-021-00045-4
17. [17] M. Altun, K. Kayıkçı ve S. Irmak, “Sınıf Öğretmenliği Öğrencilerinin Mezuniyet Notlarının Regresyon Analizi ve Yapay Sinir Ağları Yöntemleriyle Tahmini,” e-Uluslararası Eğitim Araştırmaları Dergisi, vol. 10, no. 3, pp. 29-43, 2019. doi:10.19160/ijer.624839
18. [18] M. Yıldız and C. Börekci, “Predicting Academic Achievement with Machine Learning Algorithms,” Journal of Educational Technology and Online Learning, vol. 3, no. 3, pp. 372-392, 2020. doi:10.31681/jetol.773206
19. [19] F. Ahmad, N. H. Ismail, and A. A. Aziz, “The prediction of students’ academic performance using classification data mining techniques,” Applied Mathematical Sciences, vol. 9, no. 129, pp. 6415-6426, 2015. doi:10.12988/AMS.2015.53289
20. [20] S. Hussain, N. A. Dahan, F. M. Ba-Alwi, and N. Ribata, “Educational Data Mining and Analysis of Students’ Academic Performance Using WEKA,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 9, no. 2, pp. 447-459, February 2018. doi:10.11591/IJEECS.V9.I2.PP447-459
21. [21] A. A. Saa, M. Al-Emran, and K. Shaalan, “Mining Student Information System Records to Predict Students’ Academic Performance,” in The International Conference on Advanced Machine Learning Technologies and Applications (AMLTA2019), A. E. Hassanien, A. T. Azar, T. Gaber, R. Bhatnagar, and M. F. Tolba, Ed., Cham: Springer International Publishing, pp. 229-239, 2020.
22. [22] E. Fernandes, M. Holanda, M. Victorino, V. Borges, R. Carvalho, and G. Van Erven, “Educational data mining: Predictive analysis of academic performance of public school students in the capital of Brazil,” J Bus Res, vol. 94, pp. 335-343, January 2019. doi:10.1016/J.JBUSRES.2018.02.012
23. [23] S. Aydın and A. E. Özkul, “Data Mining and An Application in Anadolu University Open Education System,” Journal of Research in Education and Teaching, vol. 4, no. 3, pp. 36-44, 2015.
24. [24] P. Sokkhey and T. Okazaki, “Developing Web-based Support Systems for Predicting Poor-performing Students using Educational Data Mining Techniques,” International Journal of Advanced Computer Science and Applications, vol. 11, no. 7, pp. 23-32, 2020. doi:10.14569/IJACSA.2020.0110704
25. [25] H. A. Mengash, “Using data mining techniques to predict student performance to support decision making in university admission systems,” IEEE Access, vol. 8, pp. 55462-55470, 2020. doi:10.1109/ACCESS.2020.2981905
26. [26] F. Çifçi, C. Kaleli, and S. Günal, “Predicting Instructor Performance by Feature Selection and Machine Learning Methods,” Anadolu Journal of Educational Sciences International, vol. 8, no. 2, pp. 419-440, August 2018. doi:10.18039/AJESI.454587
27. [27] V. S. R. Kumari, S. Veesa, and S. R. Chevala, “An Efficient Comparison Neural Network Methods to Evaluate Student Performance,” GRD Journal for Engineering, vol. 6, no. 1, pp. 4-7, 2020.
28. [28] P. Kaur, M. Singh, and G. S. Josan, “Classification and Prediction Based Data Mining Algorithms to Predict Slow Learners in Education Sector,” Procedia Comput Sci, vol. 57, pp. 500-508, January 2015. doi:10.1016/J.PROCS.2015.07.372
29. [29] H. S. Yıldız Aybek and M. R. Okur, “Predicting Achievement with Artificial Neural Networks: The Case of Anadolu University Open Education System,” International Journal of Assessment Tools in Education, vol. 5, no. 3, pp. 474-490, September 2018. doi:10.21449/IJATE.435507
30. [30] Ö. Özbay and H. Ersoy, “Analysis of Student Dynamism into Learning Management System through Data Mining Methods,” GUJGEF, vol. 37, no. 2, pp. 523-558, August 2017.
31. [31] A. Baltacı, “The Data Mining: Measurement of Academic Achievement in Faculty of Divinity Students by Data Mining,” Religion and Science-the Journal of the Faculty of Islamic Sciences of The University of Mus Alparslan University, vol. 1, no. 1, pp. 1-23, June 2018.
32. [32] S. Hazel Başer, O. Hökelekli, and K. Adem, “Predicting the Performance of Students Studying in Secondary Education Using Data Mining Methods,” Journal of Computer Science and Technologies, vol. 1, no. 1, pp. 22-27, June 2020.
33. [33] Ş. Can, T. Özdil, and C. Yılmaz, “Estimation of The Factors Affecting the Success of The University Students By Logistic Regression Analysis,” International Review of Economics and Management, vol. 6, no. 1, pp. 28-49, April 2018. doi:10.18825/IREMJOURNAL.349984
34. [34] V. B. Gladshiya and K. Sharmila, “An Efficient Approach of Feature Selection and Metrics for Analyzing the Risk of the Students Using Machine Learning,” 2021 International Conference on Advancements in Electrical, Electronics, Communication, Computing and Automation, ICAECA 2021, 2021. doi:10.1109/ICAECA52838.2021.9675507
35. [35] B. Abbasoğlu, “Prediction of Academic Achievements of Secondary School Students with Educational Data Mining Methods,” Veri Bilimi Dergisi, vol. 3, no. 1, pp. 1-10, 2020.
36. [36] S. Aghalarova and S. Bozkurt Keser, “Application of AutoML Technique for Predicting Academic Performance of Students,” El-Cezeri, vol. 9, no. 2, pp. 394-412, May 2022. doi:10.31202/ECJSE.946505
37. [37] E. Aydemir, “Forecasting of The Course Learning Notes by Data Mining Methods,” European Journal of Science and Technology, vol. 15, pp. 70-76, March 2019. doi:10.31590/EJOSAT.518899
38. [38] M. K. Assistant, N. Nidhi, S. Majithia, and N. Sharma, “Predictive Model for Students’ Academic Performance Using Classification and Feature Selection Techniques,” Proceedings - 2021 2nd International Conference on Computational Methods in Science and Technology, ICCMST 2021, pp. 106-111, 2021. doi:10.1109/ICCMST54943.2021.00032
39. [39] S. Bhutto, I. F. Siddiqui, Q. A. Arain, and M. Anwar, “Predicting Students’ Academic Performance Through Supervised Machine Learning,” ICISCT 2020 - 2nd International Conference on Information Science and Communication Technology, February 2020. doi:10.1109/ICISCT49550.2020.9080033
40. [40] K. Karthikeyan and P. Kavipriya, “On Improving Student Performance Prediction in Education Systems using Enhanced Data Mining Techniques,” International Journal of Advanced Research in Computer Science and Software Engineering, vol. 7, no. 5, pp. 935-941, May 2017. doi:10.23956/IJARCSSE/SV7I5/0348
41. [41] S. S. Shreem, H. Turabieh, S. Al Azwari, and F. Baothman, “Enhanced binary genetic algorithm as a feature selection to predict student performance,” Soft comput, vol. 26, no. 4, pp. 1811-1823, February 2022. doi:10.1007/S00500-021-06424-7/FIGURES/16
42. [42] A. Mueen, B. Zafar, and U. Manzoor, “Modeling and Predicting Students’ Academic Performance Using Data Mining Techniques,” International Journal of Modern Education and Computer Science, vol. 8, no. 11, pp. 36, November 2016. doi:10.5815/IJMECS.2016.11.05
43. [43] J. Gajwani and P. Chakraborty, “Students’ Performance Prediction Using Feature Selection and Supervised Machine Learning Algorithms,” in International Conference on Innovative Computing and Communications, A. and B. S. and H. A. E. and A. S. and J. A. Gupta Deepak and Khanna, Ed., Singapore: Springer Singapore, pp. 347-354, 2021.
44. [44] R. Bertolini, S. J. Finch, and R. H. Nehm, “Enhancing data pipelines for forecasting student performance: integrating feature selection with cross-validation,” International Journal of Educational Technology in Higher Education, vol. 18, no. 1, pp. 1-23, December 2021. doi:10.1186/S41239-021-00279-6/FIGURES/8
45. [45] S. Aghalarova and S. Bozkurt Keser, “Prediction of Secondary School Students' Academic Performance with Proposed Artificial Neural Networks Algorithm,” Veri Bilimi, vol. 4, no. 2, pp. 19-32, August 2021.
46. [46] Y. Özkan, F. Önay Koçoğlu, and Ç. Selçukcan Erol, “Prediction of Student Performance By Deep Learning Algorithm,” in 7th International Conference on “Innovations in Learning for the Future”: Digital Transformation in Education, S. Gülseçen, Ç. Selçukcan Erol, Z. Ayvaz Reis, and Gezer Murat, Ed., İstanbul: Istanbul University Press, pp. 136-144, 2018.
47. [47] W. Punlumjeak and N. Rachburee, “A comparative study of feature selection techniques for classify student performance,” in 7th International Conference on Information Technology and Electrical Engineering: Envisioning the Trend of Computer, Information and Engineering, ICITEE 2015, 29-30 Sept. 2015, Mai, Thailand, 2015. pp. 425-429. doi:10.1109/ICITEED.2015.7408984
48. [48] Y. Yakupoğlu, “Eğitimsel veri madenciliği ve bir uygulaması,” Yüksek Lisans Tezi, İstanbul Teknik Üniversitesi, İstanbul, 2018.
49. [49] M. Kumar, Nidhi, B. Sharma, and D. Handa, “Building Predictive Model by Using Data Mining and Feature Selection Techniques on Academic Dataset,” International Journal of Modern Education and Computer Science, vol. 14, no. 4, pp. 29, August 2022. doi:10.5815/IJMECS.2022.04.02
50. [50] M. Ramaswami and R. Bhaskaran, “A Study on Feature Selection Techniques in Educational Data Mining,” J Comput, vol. 1, no. 1, pp. 711, December 2009.
51. [51] V. N. Uzel, S. S. Turgut, and S. A. Özel, “Prediction of Students’ Academic Success Using Data Mining Methods,” in Innovations in Intelligent Systems and Applications Conference, ASYU 2018, Adana, Türkiye , 4-6 November 2018, Buse Melis Ozyildirim, Tülay Yildirim, Eds. IEEE, 2018. doi:10.1109/ASYU.2018.8554006
52. [52] D. Şengür, “Öğrencilerin akademik başarılarının veri madenciliği metotları ile tahmini,” Fırat Üniversitesi, Elazığ, 2013.
53. [53] M. Zaffar, M. A. Hashmani, K. S. Savita, and S. S. H. Rizvi, “A Study of Feature Selection Algorithms for Predicting Students Academic Performance,” International Journal of Advanced Computer Science and Applications, vol. 9, no. 5, pp. 541-549, 2018. doi:10.14569/IJACSA.2018.090569
54. [54] A. Acharya and D. Sinha, “Early Prediction of Students Performance using Machine Learning Techniques,” Int J Comput Appl, vol. 107, no. 1, pp. 37-43, December 2014. doi:10.5120/18717-9939
55. [55] P. Cortez and A. Silva, “Using Data Mining to Predict Secondary School Student Performance,” in Proceedings of 5th Annual Future Business Technology Conference, Porto, Portugal, 9-11 Ap. 2008, pp. 5-12.