İNTERNET BAĞIMLILIĞI SKORLARININ TAHMİNİNDE FARKLI MAKİNE ÖĞRENME MODELLERİNİN KARŞILAŞTIRILMASI

Year 2024, Issue: 50, 273 - 286, 31.12.2024

Serpil Sevimli Deniz

https://doi.org/10.61904/sbe.1567234

Abstract

Bu çalışmada, internet bağımlılığı skorlarını tahmin etmek amacıyla kullanılan farklı makine öğrenme modelleri karşılaştırılmıştır. Logistic Regression, K-Nearest Neighbors (KNN), Random Forest, Decision Tree, Support Vector Regression (SVR) ve Gradient Boosting gibi yaygın algoritmalar değerlendirilmiştir. Modellerin performansı ortalama hata kareleri (MSE) ve R² skorları ile ölçülmüştür. Sonuçlar, Random Forest ve Decision Tree modellerinin en yüksek doğruluğa sahip olduğunu, özellikle ensemble yöntemlerin internet bağımlılığı gibi çok boyutlu ve karmaşık sosyal problemleri tahmin etmede daha etkili olduğunu ortaya koymuştur. Bu çalışma, makine öğrenimi tekniklerinin sosyal bilimler ve psikoloji alanlarında uygulanabilirliğini göstererek, internet bağımlılığı tahmininde model çeşitliliğinin performansa olan etkisini analiz etmektedir.

Keywords

İnternet Bağımlılığı , Makine Öğrenimi , Logistic Regression , KNN , Random Forest , Decision Tree , SVR , Gradient Boosting

References

• Altıntop, M. (2023). Yapay Zekâ/Akıllı Öğrenme Teknolojileriyle Akademik Metin Yazma: Chatgpt Örneği. Süleyman Demirel Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, (46), 186-211.
• Altman, N. S. (1992). An introduction to kernel and nearest-neighbor nonparametric regression. The American Statistician, 46(3), 175–185. https://doi.org/10.2307/2685209.
• Alzboon, M. S., Al-Batah, M. S., Alqaraleh, M., Abuashour, A., & Bader, A. F. H. (2023). Early Diagnosis of Diabetes: A Comparison of Machine Learning Methods. International Journal of Online and Biomedical Engineering (iJOE). https://doi.org/10.3991/ijoe. v19i15.42417.
• Breiman, L. (1996). Bagging predictors. Machine Learning, 24(2), 123–140. https://doi.org/10.1007/BF00058655 Çelik, S., Atak, H. & Başal, A. (2012). Predictive role of personality traits on internet addiction. The Turkish Online Journal of Distance Education, 13(1), 10-24. https://doi.org/10.17718/TOJDE.12937.
• Dietterich, T. G. (2000). Ensemble methods in machine learning. In International workshop on multiple classifier systems (pp. 1–15). Springer. https://doi.org/10.1007/3-540-45014-9_1
• Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29(5), 1189–1232. https://doi.org/10.1214/aos/1013203451
• Fioravanti, G., & Casale, S. (2015). Evaluation of the psychometric properties of the Italian Internet Addiction Test. Cyberpsychology, Behavior and Social Networking, 18(2), 120-128. https://doi.org/ 10.1089/cyber.2014.0493.
• Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press. Hussain, I., Cakir, O., & Ozdemir, B. (2020). Studying internet addiction profile of university students with latent class analysis. Education and Information Technologies. https://doi.org/10.1007/s10639-020-10203-6.
• Lai, C. M., Mak, K. K., Watanabe, H., Ang, R. P., Pang, J. S. & Ho, R. C. (2013). Psychometric properties of the Internet Addiction Test in Chinese adolescents. Journal of Pediatric Psychology, 38(7), 794-807. https://doi.org/10.1093/jpepsy/jst022.
• Li, K., Shi, Q., Liu, S. & Xie, Y. (2021). Predicting in-hospital mortality in ICU patients with sepsis using gradient boosting decision tree. Medicine, 100(21). https://doi.org/10.1097/MD.0000000000025 813.
• Mudawi, N. A., & Alazeb, A. (2022). A Model for Predicting Cervical Cancer Using Machine Learning Algorithms. Sensors (Basel, Switzerland), 22(11), 4132. https://doi.org/10.3390/s22114132
• Rahim, A. A., & Buniyamin, N. (2022). Predicting Engineering Students' Academic Performance using Ensemble Classifiers- A Preliminary Finding. Journal of Electrical & Electronic Systems Research. https://doi.org/10.24191/jeesr.v20i1.013.
• Shae, Z., & Tsai, J. (2020). Deep learning mechanism for pervasive internet addiction prediction. In 2020 IEEE Second International Conference on Cognitive Machine Intelligence (CogMI) (pp. 1-7). https://doi.org/10.1109/CogMI50398.2020.00011.
• Singh, A., & Babbar, S. (2017). Detecting internet addiction disorder using Bayesian Networks. In Proceedings of the 2017 International Conference on Big Data Analytics and Computational Intelligence. https://doi.org/10.1007/978-981-10-8527-7_8.
• Tan, H. T., Kit, M. H., & Handayani, D. (2023). Machine learning classification model for identifying internet addiction among university students. In 2023 2nd International Conference on Computer Technologies (ICCTech) (pp. 7-11). https://doi.org/ 10.1109/ICCTech57499.2023. 00010.
• Theng, T. H., Kit, M. H., & Handayani, D. (2023). Machine learning classification model for identifying internet addiction among university students. 2023 2nd International Conference on Computer Technologies (ICCTech), 7-11. https://doi.org/10.1109/ ICCTech57499.2023.00010.
• Zhang, J., & Xin, T. (2013). Measurement of internet addiction: An item response analysis approach. Cyberpsychology, Behavior and Social Networking, 16(6), 464-468. https://doi.org/10.1089/cyber. 2012.0525.
• Xiaoqian, Q. (2012). Research on the application of fuzzy neural network in internet addiction decision. In 2012 International Conference on Computer Science and Service System (pp. 2205-2208). https://doi.org/10.1109/CSSS.2012.548.
• Young, K. S. (1998). Caught in the Net: How to recognize the signs of internet addiction and a winning strategy for recovery. New York: John Wiley & Sons.