Kohonen Öğrenme Kuralı Yardımıyla Centroid Değerleri Güncelleme

Öz

Metin madenciliği alanında öne çıkan görevlerden birisi metin sınıflandırmadır. Konuyla ilgili çok sayıda tümevarımsal öğrenim algoritması bulunmakta olup onlardan birisi de centroid tabanlı sınıflayıcıdır. Performansı naive bayes sınıflayıcı kadar iyi olan centroid sınıflayıcıların en büyük problemi model misfittir ve bu problemin çözümü için centroid değerlerinin güncellenmesine ihtiyaç vardır. Centroid güncelleme için bugüne kadar birçok yöntem geliştirilmiş olup bu çalışmada yeni bir yöntem önerilmektedir. Önerimiz; kohonen öğrenme kuralı yardımıyla centroid değerlerinin dinamik olarak güncellenmesi üzerinedir. Bu öneriye uygun olarak veriler üzerinde deneyler yapılmış ve kohonen öğrenme kuralının centroid sınıflayıcı performansını artırdığı gözlemlenmiştir.

Anahtar Kelimeler

• centroid sınıflayıcı
• model misfit
• centroid güncelleme
• kohonen öğrenme

Updating Centroid Values Using Kohonen Learning Rule

Öz

Text classification is one of the most prominent tasks in text mining. Numerous inductive learning algorithms exist, one of which is the centroid-based classifier. Centroid classifiers, which perform as well as naive Bayes classifiers, suffer from model misfit, a major problem requiring centroid values ​​to be updated. Many methods have been developed for centroid updating, and this study proposes a new method. Our proposal involves dynamically updating centroid values ​​using the Kohonen learning rule. Experiments have been conducted on data based on this proposal, and it has been observed that the Kohonen learning rule improves centroid classifier performance.

Anahtar Kelimeler

• centroid classifier
• model misfit
• centroid updating
• kohonen learning

Kaynakça

1. Chovanec, P., et al. (2023). A survey of text classification with transformers: How wide? How large? How long? How accurate? How expensive? arXiv preprint arXiv:2311.14758.
2. Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273–297.
3. Fabrizio, S. (2002). Machine learning in automated text categorization. ACM Computing Surveys, 34(1), 1–47.
4. Guan, H., Zhou, J., & Guo, M. (2009). A class-feature-centroid classifier for text categorization. In Proceedings of the WWW Conference (pp. 1–10). Madrid, Spain.
5. Han, E.-H., & Karypis, G. (2000). Centroid-based document classification: Analysis and experimental results. In Principles of Data Mining and Knowledge Discovery (pp. 424–431).
6. Joachims, T. (1998). Text categorization with support vector machines: Learning with many relevant features. In C. N. Dellec & C. Rouveirol (Eds.), Proceedings of the 10th European Conference on Machine Learning (ECML-98) (pp. 137–142). Springer-Verlag.
7. Kohonen, T. (1984). Self-organization and associative memory. Springer-Verlag.
8. Lertnattee, V., & Theeramunkong, T. (2002). Combining homogeneous classifiers for centroid-based text classification. In Proceedings of ISCC (pp. 1034–1039).

9. Lewis, D., & Ringuette, M. (1994). Comparison of two learning algorithms for text categorization. In Proceedings of the 3rd Annual Symposium on Document Analysis and Information Retrieval.
10. Li, C. H., & Park, S. C. (2009). Combination of modified BPNN algorithms and an efficient feature selection method for text categorization. Information Processing and Management, 45(3), 329–340.
11. Li, Q., Peng, H., Li, J., Xia, C., Yang, R., Sun, L., & Yu, P. (2020). A survey on text classification: From shallow to deep learning. arXiv preprint arXiv:2008.00364.
12. Masand, B., Linoff, G., & Waltz, D. (1992). Classifying news stories using memory-based reasoning. In Proceedings of the 15th ACM International Conference on Research and Development in Information Retrieval (SIGIR-92) (pp. 59–65). ACM.
13. Öztemel, E. (2003). Yapay sinir ağları. Papatya Yayıncılık.
14. Salton, G. (1989). Automatic text processing: The transformation, analysis, and retrieval of information by computer. Addison-Wesley.
15. Takçı, H., & Soğukpınar, İ. (2004). Centroid-based language identification using letter feature set. In Proceedings of CicLing (pp. 635–645). Springer-Verlag.
16. Tan, S. (2007). Large margin drag-pushing strategy for centroid text categorization. Expert Systems with Applications, 33(1), 215–220.
17. Tan, S. (2008). An improved centroid classifier for text categorization. Expert Systems with Applications, 35(1–2), 279–285.
18. Wang, K., Ding, Y., & Han, S. C. (2023). Graph neural networks for text classification: A survey. arXiv preprint arXiv:2304.11534.