Okuma Becerilerini Yordayan Özelliklerin Belirlenmesi: Genetik Algoritma Kestirimi

Abstract

Bu araştırmayla öğrencilerin okuma becerilerini yordayan özelliklerin belirlenmesi amaçlanmıştır. Araştırmanın çalışma grubunu, PISA 2015 uygulamasına katılan 42 farklı ülkeden 5232 on beş yaş grubu öğrenci oluşturmuştur. Araştırma verileri, PISA 2015 programı verileri üzerinden sağlanmış olup, genetik algoritmalar yöntemi kestirimine dayalı regresyon modeli esasıyla analiz edilmiştir. Genetik algoritmalar yöntemi ile okuma becerilerini en iyi derecede yordayan değişkenlerden oluşan regresyon modeli için değişken seçim işlemi yapmak istenmiştir. Elde edilen sonuçlara göre, cinsiyet, baba eğitim durumu, evde internet kullanımı, evde konuşulan dil, sahip olunan e-kitap okuyucu sayısı, okuma becerisini ölçen maddeleri yanıtlama hızı ve evdeki kitap çeşitliliği ve sayısı değişkenlerinin öğrencilerin okuma becerilerini istatistiksel olarak anlamlı düzeyde yordadığı saptanmıştır. Yordama düzeyi anlamlı bulunan değişkenlerdeki farklılaşmanın öğrencilerin okuma becerilerinde de anlamlı düzeyde farklılaşmaya yol açtığı anlaşılmıştır.

Keywords

• Okuma becerileri
• yordayıcı özellikler
• regresyon
• genetik algoritmalar

Determination of the Features Predicting Reading Skills: Genetic Algorithms Estimation

Abstract

The current study aimed to determine the features predicting students’ reading skills. The study group of the study was comprised of 5232 students aged 15 years from 42 countries participating in the PISA 2015 application. The data of the study were obtained over the PISA 2015 program and analyzed by using the regression model based on the genetic algorithms method estimation. It was intended to perform a feature selection process for the regression model, which consisted of the variables that best predicted reading skills with the method of genetic algorithms. The results obtained revealed that the variables of gender, father’s education level, use of the internet at home, the language used at home, the number of e-book readers, the speed at which the items measuring the reading skill was responded and the number and variety of the books at home significantly predicted the students’ reading skills. The variation in the variables whose prediction power was found to be significant was understood to lead to a significant variation in reading skills.

Keywords

• Reading skills
• predictor features
• regression
• genetic algorithms

References

1. Adaba, H. (2016). Assessing factors affecting the students reading speed and comprehension: Manasibu secondary school grade nineth in focus: Western Wallagga Zone. International Journal of Language and Linguistics, 4(5), 165-182.
2. Adams, M. J. (1990). Beginning to read: Thinking and learning about print. Cambridge: MIT Press.
3. Ahmed, A. B. ve Elaraby, I. S. (2014). Data mining: A prediction for student's performance using classification method. World Journal of Computer Application and Technology, 2(2), 43-47.
4. Altunkaynak, A. (2009). Sediment load prediction by genetic algorithms. Advances in Engineering Software, 40(9), 928-934.
5. Bozkuş, K. (2021). Digital devices and student achievement: The relationship in PISA 2018 data. International Online Journal of Education and Teaching (IOJET), 8(3), 1560-1579.
6. Brownlee, J. (2020). Data preparation for machine learning: Data cleaning, feature selection, and data transforms in Python. Machine Learning Mastery.
7. Büyüköztürk, Ş., Çakmak, E. K., Akgün, Ö. E., Karadeniz, Ş. ve Demirel, F. (2014). Bilimsel araştırma yöntemleri (16. bs.). Ankara: Pegem.
8. Carretti, B., Toffalini, E., Saponaro, C., Viola, F. ve Cornoldi, C. (2020). Text reading speed in a language with a shallow orthography benefits less from comprehension as reading ability matures. British Journal of Educational Psychology, 90(Suppl 1), 91-104.

9. Cheung, K. C., Sit, P. S., Soh, K. C., Ieong, M. K. ve Mak, S. K. (2014). Predicting academic resilience with reading engagement and demographic variables: Comparing Shanghai, Hong Kong, Korea, and Singapore from the PISA perspective. The Asia-Pacific Education Researcher, 23(4), 895-909.
10. Coşkun, E. (2002). Lise hızlı okuma teknikleri öğretim programı ve uygulamalarının değerlendirilmesi. Eğitim Araştırmaları, 9(5), 41-51.
11. Dadandı, P.U., Dadandı, İ. ve Koca, F. (2018). PISA Türkiye sonuçlarına göre sosyoekonomik faktörler ile okuma becerileri arasındaki ilişkiler. Uluslararası Türkçe Edebiyat Kültür Eğitim Dergisi, 7(2), 1239-1252.
12. Dyson, M. C. ve Haselgrove, M. (2001). The influence of reading speed and line length on the effectiveness of reading from screen. International Journal of Human-Computer Studies, 54(4), 585-612.
13. Enders, C. K. (2010). Applied missing data analysis. New York: The Guilford Press.
14. Fraenkel, J. R. ve Wallen, N. E. (2006). How to design and evaluate research in education (6. bs.). New York: McGraw-Hill.
15. Gen, M. ve Cheng, R. (1997). Genetic algorithms and engineering design. New York: Wiley.
16. Giambona, F. ve Porcu, M. (2015). Student background determinants of reading achievement in Italy. A quantile regression analysis. International Journal of Educational Development, 44(C), 95-107.
17. Goldberg, D. E. (1989). Genetic algorithms in search, optimization and machine learning. Massachusetts: Addison-Wesley.
18. Grabe, W. ve Stoller, F. L. (2011). Teaching and researching reading. New York: Pearson Education Limited.
19. Gumus, S. ve Atalmis, E. H. (2011). Exploring the relationship between purpose of computer usage and reading skills of Turkish students: Evidence from PISA 2006. Turkish Online Journal Of Educational Technology-TOJET, 10(3), 129-140.
20. Harju-Luukkainen, H., Vettenranta, J., Ouakrim-Soivio, N. ve Bernelius, V. (2016). Differences between students’ PISA reading literacy scores and grading for mother tongue and literature at school: A geostatistical analysis of the finnish PISA 2009 data. Education Inquiry, 7(4), 29413.
21. Haupt, R. L. ve Haupt, S. E. (1998). Practical genetic algorithms. USA: Willey-Interscience Publication.
22. Karakoca, A. (2009). Çok değişkenli lineer olmayan modellerde genetik algoritma (Yayımlanmamış doktora tezi). Selçuk Üniversitesi, Konya.
23. Kintsch, W. (1988). The role of knowledge in discourse comprehension: A construction-integration model. Psychological Review, 95(2), 163–182.
24. Kuhn, M., Wickham, H. ve RStudio. (2021). Preprocessing and feature engineering steps for modeling. R package version 0.1.17. https://cran.r-project.org/web/packages/recipes/index.html adresinden erişildi.
25. Kuhn, M., Wing, J., Weston, S., Williams, A., Keefer, C., Engelhardt, A., Cooper, T., Mayer, Z., Kenkel, B., R Core Team, Benesty, M., Lescarbeau, R., Ziem, A., Scrucca, L., Tang, Y., Candan, C. ve Hunt, T. (2021). Classification and regression training. R package version 6.0-90. https://cran.r-project.org/web/packages/caret/index.html adresinden erişildi.
26. Kurnaz, H. ve Yıldız, N. (2015). Ortaokul öğrencilerinin okuma motivasyonlarının çeşitli değişkenlere göre değerlendirilmesi. Türkiye Sosyal Araştırmalar Dergisi, 19(3), 53-70.
27. Kushchu, I. (2002). Genetic programming and evolutionary generalization. IEEE Transactions on Evolutionary Computation, 6(5), 431-442.
28. Kutlu, Ö. (2004, Mayıs). Türkiye’de demokrasi anlayışının gelişmesini sağlayacak bir yol: Okuduğunu anlama becerilerinin geliştirilmesi. Uluslararası Demokrasi Eğitimi Sempozyumu’nda sunulan bildiri, On sekiz Mart Üniversitesi, Çanakkale.
29. Kutlu, Ö., Yıldırım, Ö., Bilican, S. ve Kumandaş, H. (2011). İlköğretim 5. sınıf öğrencilerinin okuduğunu anlamada başarılı olup olmama durumlarının kestirilmesinde etkili olan değişkenlerin incelenmesi. Eğitimde ve Psikolojide Ölçme ve Değerlendirme Dergisi, 2(1), 131-139.
30. Lazarus, K. (2020). Socio-demographic factors affecting reading comprehension achievement among secondary school students with learning disabilities in Ibadan, Nigeria. IAFOR Journal of Education: Language Learning in Education, 8(1), 145-157.
31. Leardi, R., Boggia, R. ve Terrile, M. (1992). Genetic algorithms as a strategy for feature selection. Journal of Chemometrics, 6(5), 267-281.
32. Leisch, F. ve Dimitriadou, E. (2021). Machine learning benchmark problems. R package version 2.1-3. https://cran.r-project.org/web/packages/mlbench/index.html adresinden erişildi.
33. Michalewicz, Z. 1996. Genetic algorithms + data structures = evolution programs (3. bs.). USA: Springer.
34. Minghua, S., Qingxian, X., Benda, Z. ve Feng, Y. (2017). Regression modelling based on improved genetic algoritm. Tehnicki vjesnik/Technical Gazette, 24(1), 63-70.
35. Mustadi, A. ve Amri, F. (2020, December). Factors affecting reading interest of elementary school students. 2nd Yogyakarta International Conference on Educational Management/Administration and Pedagogy (YICEMAP 2019) içinde (s. 15-21). Atlantis Press.
36. OECD. (2017). PISA 2015 Technical report. Paris: OECD Publishing.
37. Örkcü, H. H. (2009). Ayırma analizine matematiksel programlama ve yapay sinir ağları yaklaşımları (Yayımlanmamış doktora tezi). Gazi Üniversitesi, Ankara.
38. Özçelik, D. A. (1987). Eğitim programları ve genel öğretim yöntemi. Ankara: ÖSYM Eğitim Yayını.
39. Özdemir, E. (1993). Türkçe öğretimi. İstanbul: İnkılap Kitabevi.
40. Özdemir, M. (2017). Genetik algoritma ile doğrusal regresyonda tahmin amaçlı model seçimi. Pamukkale Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, 28, 213-233.
41. Pahmi, S., Saepudin, S., Maesarah, N., Solehudin, U. I. ve Wulandari (2018). Implementation of CART (classification and regression trees) algorithm for determining factors affecting employee performance. 2018 International Conference on Computing, Engineering, and Design (ICCED) 6-8 September 2018 içinde (s. 57-62). Bangkok: Institute of Electrical and Electronics Engineers (IEEE).
42. Paterlini, S. ve Minerva, T. (2010, June). Regression model selection using genetic algorithms. Proceedings of the 11th WSEAS International Conference on Nural Networks and 11th WSEAS International Conference on Evolutionary Computing and 11th WSEAS International Conference on Fuzzy Systems içinde (s. 19-27). World Scientific and Engineering Academy and Society (WSEAS).
43. Pitoyo, A. (2020). A meta-analysis: Factors affecting students’ reading interest in Indonesia. International Journal of Multicultural and Multireligious Understanding, 7(7), 83-92.
44. Rajchert, J. M., Żułtak, T. ve Smulczyk, M. (2014). Predicting reading literacy and its improvement in the polish national extension of the PISA study: The role of intelligence, trait and state-anxiety, socio-economic status and school-type. Learning and Individual Differences, 33, 1-11.
45. Scrucca, L. (2021). Genetic algorithms. R package version 3.2.2. https://cran.r-project.org/web/packages/GA/index.html adresinden erişildi.
46. Sever, S. (1995). Türkçe öğretimi ve tam öğrenme. Ankara: Anı Yayıncılık.
47. Silge, J., Chow, F., Kuhn, M., Wickham, H. ve RStudio. (2021). General resampling infrastructure. R package version 0.1.1. https://cran.r-project.org/web/packages/rsample/index.html adresinden erişildi.
48. Şen, Z. ve Öztopal, A. (2001). Genetic algorithms for the classification and prediction of precipitation occurrence. Hydrological Sciences Journal, 46(2), 255-267.
49. Tebekana, J. ve Cishe, E. N. (2015) Socio-cultural background factors affecting the grade 3 learners’ acquisition of english literacy (reading) skills in Mthatha Education District of South Africa. International Journal of Educational Sciences, 8(3), 557-562.
50. Temizyürek, F., Çolakoğlu, B. K. ve Coşkun, S. (2013). Dokuzuncu sınıf öğrencilerinin okuma alışkanlıklarının bazı değişkenler açısından incelenmesi. Türk Eğitim Bilimleri Dergisi, 11(2), 114-150.
51. Tolvi, J. (2004). Genetic algorithms for outlier detection and variable selection in linear regression models. Soft Computing, 8(8), 527-533.
52. Torppa, M., Eklund, K., Sulkunen, S., Niemi, P. ve Ahonen, T. (2018). Why do boys and girls perform differently on PISA reading in Finland? The effects of reading fluency, achievement behaviour, leisure reading and homework activity. Journal of Research in Reading, 41(1), 122-139.
53. Torres, L. R., Ordóñez, G. ve Calvo, K. (2021). Teacher and student practices associated with performance in the PISA reading literacy evaluation. Frontiers in Education, 6, 167.
54. Torres, R. C. (2019). Factors affecting the reading comprehension of intermediate level learners: Basis for an intervention program. https://www.researchgate.net/profile/Rossana-Torres/publication/351451654_Factors_Affecting_the_Reading_Comprehension_of_Intermediate_Level_Learners_Basis_for_An_Intervention_Program/links/609918dc299bf1ad8d8e381b/Factors-Affecting-the-Reading-Comprehension-of-Intermediate-Level-Learners-Basis-for-An-Intervention-Program.pdf adresinden erişildi.
55. Trejos, J., Villalobos-Arias, M. A. ve Espinoza, J. L. (2016). Variable selection in multiple linear regression using a genetic algorithm. Handbook of research on modern optimization algorithms and applications in engineering and economics içinde (s. 133-159). IGI Global.
56. Uysal, P. K. ve Bilge, H. (2018). An investigation on the relationship between reading fluency and level of reading comprehension according to the type of texts. International Electronic Journal of Elementary Education, 11(2), 161-172.
57. Vasant, P. M. (2013). Meta-heuristics optimization algorithms in engineering, business, economics, and finance. Hershey, PA: IGI Global.
58. Wickham, H. ve RStudio. (2020). Modelling functions that work with the pipe. R package version 0.1.8. https://cran.r-project.org/web/packages/modelr/index.html adresinden erişildi.
59. Williams, J. P. (2003). Teaching text structure to improve reading comprehension. H. L. Swanson, K. R. Harris, & S. Graham (Eds.). Handbook of learning disabilities içinde (s. 293–305). New York: The Guilford Press.
60. Yalçın, S. (2018). 21. yüzyıl becerileri ve bu becerilerin ölçülmesinde kullanılan araçlar ve yaklaşımlar. Ankara University Journal of Faculty of Educational Sciences (JFES), 51(1), 183-201.
61. Yang, C. Y., Jeng, J. T., Chuang, C. C. ve Tao, C. W. (2011, June). Constructing the linear regression models for the symbolic interval-values data using PSO algorithm. Proceedings 2011 International Conference on System Science and Engineering içinde (s. 177-181). IEEE.
62. Yıldız, M. ve Akyol, H. (2011). İlköğretim 5. Sınıf öğrencilerinin okuduğunu anlama, okuma motivasyonu ve okuma alışkanlıkları arasındaki ilişki. Gazi Eğitim Fakültesi Dergisi, 31(3), 793-815.
63. Žegklitz, J. ve Pošík, P. (2015, July). Model selection and overfitting in genetic programming: Empirical study. Proceedings of the Companion Publication of the 2015 Annual Conference on Genetic and Evolutionary Computation içinde (s. 1527-1528).