Eğitimde Kullanılan Erken Uyarı Sistemleri Konusunda Yapılmış Çalışmaların İncelenmesi

Year 2021, Volume: 10 Issue: 2, 788 - 797, 19.04.2021

Abdullatif Kaban , Ömer Bilen

https://doi.org/10.33206/mjss.816902

Abstract

Veri madenciliği ve yapay zekâ teknolojilerinin ilerlemesiyle öğrencilerin öğretim yönetim sistemleri üzerindeki hareketlerine bakarak geleceğe yönelik davranışları tahmin edilebilir hale gelmiştir. Özellikle riskli öğrencilerin önceden tespit edilerek uyarı vermesi mantığına dayanan erken uyarı sistemleri geliştirilerek uzaktan eğitim veren kurumlara bilgi sağlanmaktadır. Çalışmamızın amacı, erken uyarı sistemleri üzerine yapılan çalışmaların yayın özellikleri ve veri madenciliğine dayalı analiz yöntemi özellikleri açısından incelenerek mevcut durumun ortaya çıkarılmasıdır. Bu amaç doğrultusunda Google Akademik veri tabanından elde edilen veriler içerik analizi yöntemi ile incelenmiş ve elde edilen sonuçlar frekans tabloları halinde sunulmuştur. Erken Uyarı Sistemleri üzerine yapılan çalışmalar incelendiğinde, bu başlıktaki çalışmalara 2014 yılından sonra başlandığı ve 2018 yılında konu ile ilgili çalışma sayısının arttığı görülmüştür. Bu çalışmaların çoğunlukla ABD’de yapıldığı, makale ve bildiri türünde olduğu ve nicel yöntemlerin tercih edildiği tespit edilmiştir. Yapılan deneysel çalışmalarda verilerin, öğrenme yönetim sisteminden alınan sistem kayıtlarından toplandığı ve verilerin çeşitli veri madenciliği teknikleri kullanılarak analiz edildiği sonucuna varılmıştır. Erken uyarı sistemleri konusunda uygulanabilirliği kanıtlanmış bir modelin henüz geliştirilememiş olması bu çalışmadan elde edilen en önemli sonuç olarak değerlendirilebilir.

Keywords

Erken Uyarı Sistemleri, Öğrenme Yönetim Sistemi, Öğrenme Analitkleri, Veri Madenciliği

Review of Studies on Early Warning Systems Used in Education

Abstract

The development of data mining and artificial intelligence technologies has led to the fact that the future behavior of students has become predictable when looking at their actions in learning management systems. In particular, early warning systems based on the logic of identify at-risk students and give warnings to them are developed and provide information to distance education institutions. This study aims to examine studies of early warning systems used in education in terms of publication characteristics and data mining analysis methods, as well as to identify the current situation. For this purpose, the data obtained from the Google Scholar database was examined by the content analysis method and the results were presented in frequency tables. When the studies on Early Warning Systems were examined, it was seen that the studies on this topic started after 2014 and the number of studies related to the subject increased in 2018. It was found that these studies were mainly conducted in the United States, represented by articles and conference reports, and the preference was given to quantitative methods. Pilot studies concluded that data was collected from system records taken from a learning management system and that the data was analyzed using a variety of data mining techniques. It can be said that a model that has proven applicability in early warning systems has not been developed yet and this is one of the important results obtained from this study.

Keywords

Early Warning Systems, Learning Management System, Learning Analytics, Data Mining

References

• Akçapınar, G., Altun, A., & Aşkar, P. (2019). Using learning analytics to develop early-warning system for at-risk students. International Journal of Educational Technology in Higher Education, 16(40), 1-20. doi: 10.1186/s41239-019-0172-z
• Akçapınar, G., Hasnine, M., Majumdar, R., Flanagan, B., & Ogata, H. (2019). Developing an early-warning system for spotting at-risk students by using eBook interaction logs. Smart Learning Environments, 6(4). doi: 10.1186/s40561-019-0083-4
• Aly, M., & Hasan, M. (2019). Improving STEM Performance by Leveraging Machine Learning Models. Int'l Conf. Frontiers in Education: CS and CE (FECS'19), (pp. 205-211).
• Arnold, K. (2017). The Effects of Educational Technology Usage Profiles and Legally Protected Bio-Demographic Data on Behaviorally Based Predictive Student Success Models in Learning Analytics: An Exploratory Study (Doctoral Dissertation). Purdue University.
• Baneres, D., Rodriguez-Gonzalez, M. E., & Serra, M. (2019). An Early Feedback Prediction System for Learners At-Risk Within a First-Year Higher Education Course. IEEE Transactions on Learning Technologies, 12(2), 249-263. doi: 10.1109/TLT.2019.2912167
• Brown, M., DeMonbrun, R., & Teasley, S. (2018). Taken Together: Conceptualizing Students’ Concurrent Course Enrollment across the Post-Secondary Curriculum Using Temporal Analytics. The Journal of Learning Analytics, 5(3), 60-72. doi: 10.18608/jla.2018.53.5
• Büyüköztürk, Ş., Kılıç Çakmak, E., Akgün, Ö. E., Karadeniz, Ş. ve Demirel, F. (2009). Bilimsel Araştırma Yöntemleri. Ankara: Pegem Akademi.
• Cohen, L., Manion, L., & Morrison, K. (2007). Research Methods in Education. Taylor & Francis e-Library.
• DeGraff, J., DeGraff, N., & Romesburg, H. (2013). Literature searches with Google Scholar: Knowing what you are and are not getting. GSA Today, 23(10), 44-45. doi: 10.1130/GSAT175GW.1
• Dewan, M., Lin, F., Wen, D., & Kinshuk. (2015). Predicting Dropout-Prone Students in E-Learning Education System. UIC-ATC-ScalCom-CBDCom-IoP 2015, (pp. 1735-1740). Beijing, China. doi: 10.1109/UIC-ATC-ScalCom-CBDCom-IoP.2015.315
• Elbadrawy, A., Polyzou, A., Ren, Z., Sweeney, M., Karypis, G., & Rangwala, H. (2016). Predicting Student Performance Using Personalized Analytics. Computer, 49(4), 61-69. doi: 10.1109/MC.2016.119
• He, L., Levine, R., Bohonak, A., Fan, J., & Stronach, J. (2018). Predictive Analytics Machinery for STEM Student Success Studies. Applied Artificial Intelligence, 32(4), 361–387. doi: 10.1080/08839514.2018.1483121
• Hill, F., Fulcher, D., Sie, R., & de Laat, M. (2018). Balancing Accuracy and Transparency in Early Alert Identification of Students at Risk. 2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering (TALE), (pp. 1125-1128). Wollongong, NSW, Australia. doi: 10.1109/TALE.2018.8615370
• Howard, E., Meehan, M., & Parnell, A. (2018). Contrasting prediction methods for early warning systems at undergraduate level. The Internet and Higher Education, 37, 66-75. doi: 10.1016/j.iheduc.2018.02.001
• Hung, J.-L., Shelton, B., Yang, J., & Du, X. (2019). Improving Predictive Modeling for At-Risk Student Identification: A Multistage Approach. IEEE TRANSACTIONS ON LEARNING TECHNOLOGIES, 12(2), 148-157. doi: 10.1109/TLT.2019.2911072
• Hung, J.-L., Wang, M., Wang, S., Abdelrasoul, M., Li, Y., & He, W. (2017). Identifying At-Risk Students for Early Interventions—A Time-Series Clustering Approach. IEEE Transactions on Emerging Topics in Computing, 5(1), 45-55. doi: 10.1109/TETC.2015.2504239
• Hussain, M., Zhu, W., Zhang, W., Abidi, S., & Ali, S. (2018). Using machine learning to predict student difficulties from learning session data. Artificial Intelligence Review. doi: 10.1007/s10462-018-9620-8
• Jokhan, A., Sharma, B., & Singh, S. (2018). Early warning system as a predictor for student performance in higher education blended courses. Studies in Higher Education. doi:10.1080/03075079.2018.1466872
• Kotsiantis, S. (2012). Use of machine learning techniques for educational proposes: a decision support system for forecasting students’ grades. Artificial Intelligence Review, 37(4), 331-344. doi: 10.1007/s10462-011-9234-x
• Macfadyen, L., & Dawson, S. (2010). Mining LMS data to develop an “early warning system” for educators: A proof of concept. Computers & Education, 54(2), 588-599. doi: 10.1016/j.compedu.2009.09.008
• Marbouti, F., Diefes-Dux, H., & Madhavan, K. (2015). Predictive modeling for identifying at-risk students using course performance data. The 6th Research in Engineering Education Symposium. Ireland, Dublin.
• Marbouti, F., Diefes-Dux, H., & Madhavan, K. (2016). Models for early prediction of at-risk students in a course using standards-based grading. Computers & Education, 103, 1-15. doi: 10.1016/j.compedu.2016.09.005
• Mduma, N., Kalegele, K., & Machuve, D. (2019). A Survey of Machine Learning Approaches and Techniques for Student Dropout Prediction. Data Science Journal, 18(14), 1-10. doi: 10.5334/dsj-2019-014
• Mi, C. (2019). Student Performance Early Warning based on Data Mining. International Journal of Performability Engineering, 15(3), 822-833.
• Samson, P., Czarnik, A., & Gross, M. (2017). Relationships Between Digital Measures of Student Engagement and Exam Scores: Is the LMS Enough? 7th International Learning Analytics & Knowledge Conference (LAK17): Practitioner Track, (pp. 106-117). Vancouver, Canada.
• Sandoval, A., Gonzalez, C., Alarcon, R., Pichara, K., & Montenegro, M. (2018). Centralized student performance prediction in large courses based on lowcost variables in an institutional context. The Internet and Higher Education, 37, 76-89. doi: 10.1016/j.iheduc.2018.02.002
• Sclater, N., Peasgood, A., & Mullan, J. (2016). Learning analytics in higher education: A review of UK and international practice. London: Jisc.
• Sezer, A. (1994). Türkiyede bitki hastalıklarının savaşımında kullanılan ön tahmin ve erken uyarı sistemleri (Yüksek Lisans Tezi). Ankara Üniversitesi / Fen Bilimleri Enstitüsü.
• Stapel, M., Zheng, Z., & Pinkwart, N. (2016). An Ensemble Method to Predict Student Performance in an Online Math Learning Environment. 9th International Conference on Educational Data Mining, (pp. 231-238). Raleigh, NC.
• Tempelaar, D., Rienties, B., & Giesbers, B. (2015). In search for the most informative data for feedback generation: Learning Analytics in a data-rich context. Computers in Human Behavior, 47, 157-167. doi: 10.1016/j.chb.2014.05.038
• Waddington, R., Nam, S., Lonn, S., & Teasley, S. (2016). Improving Early Warning Systems with Categorized Course Resource Usage. Journal of Learning Analytics, 3(3), 263-290. doi: 10.18608/jla.2016.33.13
• Yıldırım, A., & Şimşek, H. (2005). Sosyal bilimlerde nitel araştırma yöntemleri (5. Baskı). Ankara: Seçkin Yayıncılık.
• Yuxiang, W. (2019). Academic Supervision and Risk Assessment Based on Moodle LMS Data. 2019 International Conference on Robots & Intelligent System (ICRIS). Warsaw, Poland. doi: 10.1109/ICRIS.2019.00075