Dördüncü sınıf Türk öğrencilerinin okuma performansının yordayıcıları

Year 2025, Volume: 14 Issue: 1, 1 - 18, 31.01.2025

Kıvanç Bozkuş

https://doi.org/10.19128/turje.1431545

Abstract

Makine öğrenimini kullanan bu araştırma, PIRLS 2021'e katılan Türkiye'den dördüncü sınıf öğrencilerinin okuma performansını yordayan önemli faktörleri ortaya çıkarmak amacıyla yapılmıştır. Destek vektörleri makine (SVM) algoritması, 3589 dördüncü sınıf öğrencisine ait 405 bağımsız değişkeninin verileriyle eğitildiğinde, okul, öğretmen ve aile düzeyindeki 16 temel bağlamsal faktöre dayanarak yüksek ve düşük performans gösteren öğrencileri doğru bir şekilde ayırmıştır. Ana faktörler okul düzeyindedir ve bunlar öğretime ve öğrencilerin kitap ödünç alma becerisine büyük önem verilmesiyle ilgilidir. Öğretmen düzeyindeki faktörler ise değerlendirme stratejisi, öğrencilerin okuduğunu anlama becerilerini veya stratejilerini geliştirmelerine yardımcı olma ve motivasyondur. Aile düzeyindeki tek faktör, ebeveynlerin öğrencilerin öğrenmeye hazır olmalarını sağlama konusundaki kararlılığıdır. PIRLS 2021 verilerinin tamamıyla karşılaştırıldığında bu araştırmanın bulguları, Türkiye'deki dördüncü sınıf öğrencilerinin okuma performansını öngören temel faktörlerde büyük bir fark olduğunu ortaya çıkarmıştır. Olası nedenler tartışılmış ve yeni eğitim politikaları, müdahaleler ve araştırma uygulamaları önerilmiştir. Politika düzeyinde, okul, öğretmen ve aile faktörlerini sistemli bir şekilde ele alan bir yaklaşımın, okuma performansında daha anlamlı iyileştirmelere yol açabileceği belirtilmiştir. Müdahaleler açısından, bulgular, öğrencilerin metinle aktif olarak etkileşime girdiği etkileşimli öğretim ve değerlendirme stratejilerine odaklanmanın gerekliliğini öne sürmektedir. Araştırma uygulamaları açısından, bu çalışma, öğrenci performansının karmaşık, çok boyutlu doğasını anlamak için makine öğreniminin önemli bir araç olarak potansiyelini vurgulamaktadır.

Keywords

Makine öğrenmesi, Okuma performansı, PIRLS, SVM, Türkiye

Ethical Statement

Since this study uses a public dataset available online at pirls2021.org/data, ethics committee approval is not required.

Predictors of reading performance of fourth-grade Turkish students

Abstract

Using machine learning, this research aimed to examine the crucial factors that predict the reading performance of fourth-grade students from Türkiye who participated in PIRLS 2021. When trained with the data of 3589 fourth-grade students and their 405 independent variables, the support vector machine (SVM) algorithm properly distinguished between high- and low-performing students based on 16 key contextual factors at the school, teacher, and family levels. The main factors were at the school level and were related to placing a major emphasis on instruction and the ability of students to borrow books. The teacher-level factors were the assessment strategy, helping students develop reading comprehension skills or strategies, and motivation. The only family-level factor was the parental commitment to ensure that students are ready to learn. Compared to the results of the whole PIRLS 2021 data, the findings of this research revealed a big difference in the key factors predicting the reading performance of fourth graders from Türkiye. Possible reasons were discussed, and new educational policies, interventions, and research practices were suggested. At the policy level, an approach that systemically addresses school, teacher, and family factors may yield more meaningful improvements in reading performance. In terms of interventions, the findings suggest a focus on interactive teaching and assessment strategies that involve students actively interacting with text. As for research practices, this study highlighted the potential of machine learning as a valuable tool to understand the complex, multi-dimensional nature of student performance.

Keywords

Machine learning, PIRLS, Reading performance, SVM, Türkiye

Ethical Statement

Since this study uses a public dataset available online at pirls2021.org/data, ethics committee approval is not required.

References

• Albashish, D., Hammouri, A. I., Braik, M., Atwan, J., & Sahran, S. (2021). Binary biogeography-based optimization based SVM-RFE for feature selection. Applied Soft Computing, 101, 107026-107026. https://doi.org/10.1016/j.asoc.2020.107026
• Allington, R. L., & McGill-Franzen, A. M. (2021). Reading volume and reading achievement: A review of recent research. Reading Research Quarterly, 56(S1), 231-238. https://doi.org/10.1002/rrq.404
• Alruwais, N., & Zakariah, M. (2023). Evaluating student knowledge assessment using machine learning techniques. Sustainability, 15(7), 6229-6229. https://doi.org/10.3390/su15076229
• Ameyaw, S. K., & Anto, S. K. (2018). Read or perish: Reading habits among students and its effect on academic performance: A case study of Eastbank Senior High School-Accra. Library Philosophy and Practice, 1-23.
• Archibald, S. L. (2006). Narrowing in on educational resources that do affect student achievement. Peabody Journal of Education, 81(4), 23-42. https://doi.org/10.1207/s15327930pje8104_2
• Avolio, M., & Fuduli, A. (2021). A semiproximal support vector machine approach for binary multiple instance learning. IEEE Transactions on Neural Networks and Learning Systems, 32(8), 3566-3577. https://doi.org/10.1109/tnnls.2020.3015442
• Bannister, S. L., Hanson, J. L., Maloney, C. G., & Dudas, R. A. (2015). Practical framework for fostering a positive learning environment. Pediatrics, 136(1), 6-9. https://doi.org/10.1542/peds.2015-1314
• Bernardo, A. B. I., Cordel, M. O., Lucas, R. I. G., Teves, J. M. M., Yap, S. A., & Chua, U. (2021). Using machine learning approaches to explore non-cognitive variables influencing reading proficiency in English among Filipino learners. Education Sciences, 11(10), 628-628. https://doi.org/10.3390/educsci11100628
• Bozkuş, K. (2025). Predictors of reading performance of fourth-graders. Manuscript submitted for publication.
• Chen, F., Sakyi, A., & Cui, Y. (2022). Identifying key contextual factors of digital reading literacy through a machine learning approach. Journal of Educational Computing Research, 60(7), 1763-1795. https://doi.org/10.1177/07356331221083215
• Chen, J., Zhang, Y., Wei, Y., & Hu, J. (2019). Discrimination of the contextual features of top performers in scientific literacy using a machine learning approach. Research in Science Education, 51, 129-158. https://doi.org/10.1007/s11165-019-9835-y
• Dong, X. L., & Hu, J. (2019). An exploration of impact factors influencing students’ reading literacy in Singapore with machine learning approaches. International Journal of English Linguistics, 9(5), 52-52. https://doi.org/10.5539/ijel.v9n5p52
• Eker, C. (2014). The effect of teaching practice conducted by using metacognition strategies on students’ reading comprehension skills. International Online Journal of Educational Sciences, 6(2), 269-280. https://doi.org/10.15345/iojes.2014.02.002
• Frijters, J. C., Tsujimoto, K. C., Boada, R., Gottwald, S., Hill, D. E., Jacobson, L. P., Lovett, M. W., Mahone, E. M., Willcutt, E. G., & Wolf, M. (2018). Reading-related causal attributions for success and failure: Dynamic links with reading skill. Reading Research Quarterly, 53(1), 127-148. https://doi.org/10.1002/rrq.189
• Gorostiaga, A., & Rojo-Alvarez, J. L. (2016). On the use of conventional and statistical learning techniques for the analysis of PISA results in Spain. Neurocomputing, 171, 625-637. https://doi.org/10.1016/j.neucom.2015.07.001
• Hill, N. E., & Tyson, D. F. (2009). Parental involvement in middle school: A meta-analytic assessment of the strategies that promote achievement. Developmental Psychology, 45(3), 740-763. https://doi.org/10.1037/a0015362
• Hu, J., Dong, X., & Peng, Y. (2022). Discovery of the key contextual factors relevant to the reading performance of elementary school students from 61 countries/regions: insight from a machine learning-based approach. Reading and Writing, 35, 93-127. https://doi.org/10.1007/s11145-021-10176-z
• James, N. D. (2019). A novel robust kernel for classifying high-dimensional data using Support Vector Machines. Expert Systems with Applications, 131, 116-131. https://doi.org/10.1016/j.eswa.2019.04.037
• Jeynes, W. H. (2007). The relationship between parental involvement and urban secondary school student academic achievement: A meta-analysis. Urban Education, 42(1), 82-110. https://doi.org/10.1177/0042085906293818
• Kettler, T. (2014). Critical thinking skills among elementary school students: Comparing identified gifted and general education student performance. Gifted Child Quarterly, 58(2), 127-136. https://doi.org/10.1177/0016986214522508
• Kikas, E., Soodla, P., & Mägi, K. (2018). Teacher Judgments of Student Reading and Math Skills: Associations With Child- and Classroom-Related Factors. Scandinavian Journal of Educational Research, 62(5), 783-797. https://doi.org/10.1080/00313831.2017.1307271
• Krashen, S. D. (2004). The Power of Reading: Insights from the Research. Libraries Unlimited.
• Latif, G., Alghazo, J., Butt, M. J., & Kazimi, Z. (2021). Fast parallel SVM based arrhythmia detection on multiple GPU clusters. 2021 10th IEEE International Conference on Communication Systems and Network Technologies (CSNT), 669-673. https://doi.org/10.1109/csnt51715.2021.9509589
• Law, Y. (2011). The role of teachers’ cognitive support in motivating young Hong Kong Chinese children to read and enhancing reading comprehension. Teaching and Teacher Education, 27(1), 73-84. https://doi.org/10.1016/j.tate.2010.07.004
• Leahy, M. A., & Fitzpatrick, N. M. (2017). Early readers and academic success. Journal of Educational and Developmental Psychology, 7(2), 87-95. https://doi.org/10.5539/jedp.v7n2p87
• Lee, J., & Shute, V. J. (2010). Personal and social-contextual factors in K–12 academic performance: An integrative perspective on student learning. Educational Psychologist, 45(3), 185-202. https://doi.org/10.1080/00461520.2010.493471
• Lewis, N. D. (2017). Machine learning made easy with R. ND Lewis.
• Lim, H. J., Bong, M., & Woo, Y. K. (2015). Reading attitude as a mediator between contextual factors and reading behavior. Teachers College Record, 117(1), 1-36. https://doi.org/10.1177/016146811511700108
• Lin, X., & Powell, S. R. (2022). The roles of initial mathematics, reading, and cognitive skills in subsequent mathematics performance: A meta-analytic structural equation modeling approach. Review of Educational Research, 92(2), 288-325. https://doi.org/10.3102/00346543211054576
• Mullis, I.V.S., von Davier, M., Foy, P., Fishbein, B., Reynolds, K.A., & Wry, E. (2023). PIRLS 2021 International Results in Reading. Boston College, TIMSS & PIRLS International Study Center. https://doi.org/10.6017/lse.tpisc.tr2103.kb5342
• Ouellette, G., & Haley, A. (2013). One complicated extended family: The influence of alphabetic knowledge and vocabulary on phonemic awareness. Journal of Research in Reading, 36(1), 29-41. https://doi.org/10.1111/j.1467-9817.2010.01483.x
• Pallathadka, H., Sonia, B., Sanchez, D. T., De Vera, J. V., Godinez, J. A. T., & Pepito, M. T. (2022). Investigating the impact of artificial intelligence in education sector by predicting student performance. Materials Today: Proceedings, 51, 2264-2267. https://doi.org/10.1016/j.matpr.2021.11.395
• Park, H. (2008). Home literacy environments and children's reading performance: A comparative study of 25 countries. Educational Research and Evaluation, 14(6), 489-505. https://doi.org/10.1080/13803610802576734
• Rosenblatt, L. M. (1995). Literature as exploration (5th ed.). Modern Language Association.
• Savolainen, H., Ahonen, T., Aro, M., Tolvanen, A., & Holopainen, L. (2008). Reading comprehension, word reading and spelling as predictors of school achievement and choice of secondary education. Learning and Instruction, 18(2), 201-210. https://doi.org/10.1016/j.learninstruc.2007.09.017
• Shimoda, A., Ichikawa, D., & Oyama, H. (2018). Using machine-learning approaches to predict non-participation in a nationwide general health check-up scheme. Computer Methods and Programs in Biomedicine, 163, 39-46. https://doi.org/10.1016/j.cmpb.2018.05.032
• Swain-Bradway, J., Pinkney, C., & Flannery, K. B. (2015). Implementing schoolwide positive behavior interventions and supports in high schools: Contextual factors and stages of implementation. Teaching Exceptional Children, 47(5), 245-255. https://doi.org/10.1177/0040059915580030
• Wang, M. T., & Degol, J. L. (2016). School climate: A review of the construct, measurement, and impact on student outcomes. Educational Psychology Review, 28(2), 315-352. https://doi.org/10.1007/s10648-015-9319-1
• Wolniak, G. C., & Engberg, M. E. (2010). Academic achievement in the first year of college: Evidence of the pervasive effects of the high school context. Research in Higher Education, 51, 451-467. https://doi.org/10.1007/s11162-010-9165-4