ÖĞRENCİLERİN STEM KARİYER TERCİHLERİNİN VERİ MADENCİLİĞİ YAKLAŞIMI İLE TAHMİN EDİLMESİ

Bu çalışmada ortaokul öğrencilerinin, ASSISTments isimli zeki öğretim sistemindeki etkileşim verileri kullanılarak, eğitim ve mesleki kariyerlerine STEM ile ilgili bir alanda devam edip etmeyeceklerini tahmin edecek bir model oluşturulması amaçlanmıştır. Analizler 2017 yılında aynı amaçla düzenlenen ASSISTments Veri Madenciliği Yarışması’nda (ASSISTments Data Mining Competition 2017) katılımcılara sunulan veri seti ile gerçekleştirilmiştir. Veri seti, 2004-2007 yılları arasında sistemi kullanan 1709 öğrenciye ilişkin yaklaşık 1 milyon satırlık tıklama verisini içermektedir. Veriler, öğrencileri tanımlayan bilgiler silinerek katılımcılara sunulmuştur. Veri setinde 514 öğrencinin STEM kariyerine devam edip etmedikleri bilgisini içeren bir eğitim veri seti yer almaktadır. Tahmin modeli oluşturmak amacıyla Random Forest (RF), kNN, SVM (Support Vector Machine) ve GMB (Generalized Regression Models Boosted) algoritmaları kullanılmıştır. Veri setinde STEM tercih eden ve etmeyen öğrenciler arasında dengesiz dağılım bulunmaktadır. Bu nedenle farklı veri dengeleme yöntemlerinin modellerin tahmin performansına etkisi de test edilmiştir. Sonuçların değerlendirilmesi için 10-katlı çapraz geçerlilik yöntemi kullanılmıştır. Yapılan analizler sonucunda en iyi sınıflama performansına SVM algoritması ile yukarı örnekleme yönteminin birlikte kullanıldığı durumda ulaşılmıştır. Bu durumda oluşturulan tahmin modeli, STEM kariyeri tercih eden öğrencilerin %66’sını doğru olarak tahmin etmiştir. Aynı zamanda öğrencilerin STEM kariyer tercihlerini belirlemede önemli olan değişkenler de analiz edilmiştir.

PREDICTING STUDENTS’ STEM CAREER INTERESTS BY USING DATA MINING APPROACH

In this study, it is aimed at creating a model that will predict whether secondary school students will continue their education and professional careers in an area related to STEM or not. Interaction dataset made available to the participants in ASSISTments Data Mining Competition 2017 is analyzed. This anonymized dataset consists of approximately 1 million click-stream records collected from 1709 students who used the intelligent tutoring system between 2004-2007. The dataset also contained a training dataset that includes information about whether 514 students in the dataset continued their STEM careers or not. For prediction, the performance of the Random Forest (RF), kNN, SVM (Support Vector Machine) and GMB (Generalized Regression Models Boosted) algorithms are compared. There was a class imbalance problem in training dataset, therefore, we compared various data balancing algorithms’ effect on the prediction algorithms. A 10-fold cross-validation was used to evaluate the performance of prediction models. As a result, the best performance was obtained when SVM algorithm and oversampling method were used together. In this case, the prediction model predicted over the students who prefer STEM careers with an accuracy of 66%. Features that are important while predicting STEM career preferences of students were also analyzed.

PDF

___

Baker, R. S. J. d. (2007). Modeling and understanding students' off-task behavior in intelligent tutoring systems. Paper presented at the Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, San Jose, California, USA.
Chawla, N. V. (2005). Data Mining for Imbalanced Datasets: An Overview. In O. Maimon & L. Rokach (Eds.), Data Mining and Knowledge Discovery Handbook (pp. 853-867). Boston, MA: Springer US.
Desmarais, M. C., & Baker, R. S. (2012). A review of recent advances in learner and skill modeling in intelligent learning environments. User Modeling and User-Adapted Interaction, 22(1-2), 9-38. doi: 10.1007/s11257-011-9106-8
Feng, M., Heffernan, N., & Koedinger, K. (2009). Addressing the assessment challenge with an online system that tutors as it assesses. User Modeling and User-Adapted Interaction, 19(3), 243-266. doi: 10.1007/s11257-009-9063-7
Heffernan, N. T., & Heffernan, C. L. (2014). The ASSISTments Ecosystem: Building a Platform that Brings Scientists and Teachers Together for Minimally Invasive Research on Human Learning and Teaching. International Journal of Artificial Intelligence in Education, 24(4), 470-497. doi: 10.1007/s40593-014-0024-x
Koedinger, K., Baker, R., Cunningham, K., Skogsholm, A., Leber, B., & Stamper, J. (2010). A data repository for the EDM community: The PSLC DataShop. Handbook of educational data mining, 43. doi: citeulike-article-id:13242329
Kowarik, A., & Templ, M. (2016). Imputation with the R Package VIM. 2016, 74(7), 16. doi: 10.18637/jss.v074.i07
Kuhn, M. (2008). Building Predictive Models in R Using the caret Package. 2008, 28(5), 26. doi: 10.18637/jss.v028.i05
Olmo, J. L., Romero, C., Gibaja, E., & Ventura, S. (2015). Improving Meta-learning for Algorithm Selection by Using Multi-label Classification: A Case of Study with Educational Data Sets. International Journal of Computational Intelligence Systems, 8(6), 1144-1164. doi: 10.1080/18756891.2015.1113748
Pardos, Z. A., Baker, R. S. J. D., San Pedro, M., Gowda, S. M., & Gowda, S. M. (2014). Affective States and State Tests: Investigating How Affect and Engagement during the School Year Predict End-of-Year Learning Outcomes. 2014, 1(1), 22. doi: 10.18608/jla.2014.11.6
Pedro, M. O., Baker, R., Bowers, A., & Heffernan, N. (2013). Predicting college enrollment from student interaction with an intelligent tutoring system in middle school. Paper presented at the Educational Data Mining 2013.
Pedro, M. O., Ocumpaugh, J., Baker, R., & Heffernan, N. (2014). Predicting STEM and non-STEM college major enrollment from middle school interaction with mathematics educational software. Paper presented at the Educational Data Mining 2014.
Peña-Ayala, A. (2014). Educational data mining: A survey and a data mining -based analysis of recent works. Expert Systems with Applications, 41(4, Part 1), 1432-1462. doi: doi.org/10.1016/j.eswa.2013.08.042
R Core Team. (2017). R: A language and environment for statistical computing: R Foundation for Statistical Computing. Retrieved from https://www.R-project.org/
Refaeilzadeh, P., Tang, L., & Liu, H. (2016). Cross-Validation. In L. Liu & M. T. Özsu (Eds.), Encyclopedia of Database Systems (pp. 1-7). New York, NY: Springer New York.
San Pedro, M. O. C. Z., Baker, R. S. J. d., & Rodrigo, M. M. T. (2011). Detecting Carelessness through Contextual Estimation of Slip Probabilities among Students Using an Intelligent Tutor for Mathematics, Berlin, Heidelberg.
San Pedro, M. O. Z., Baker, R. S. J. d., Gowda, S. M., & Heffernan, N. T. (2013). Towards an Understanding of Affect and Knowledge from Student Interaction with an Intelligent Tutoring System. In H. C. Lane, K. Yacef, J. Mostow & P. Pavlik (Eds.), Artificial Intelligence in Education: 16th International Conference, AIED 2013, Memphis, TN, USA, July 9-13, 2013. Proceedings (pp. 41-50). Berlin, Heidelberg: Springer Berlin Heidelberg.
Stamper, J., Koedinger, K., Baker, R. S. J. d., Skogsholm, A., Leber, B., Rankin, J., & Demi, S. (2010). PSLC DataShop: A Data Analysis Service for the Learning Science Community, Berlin, Heidelberg.
Yu, H.-F., Lo, H.-Y., Hsieh, H.-P., Lou, J.-K., McKenzie, T. G., Chou, J.-W., . . . Lin, C.-J. (2010). Feature Engineering and Classifier Ensemble for KDD Cup 2010.