Abstract

Bu çalışmada, Türkçe dilindeki kısa mesaj hizmeti (SMS=Short Message Service) istenmeyen mesajlarının filtrelenmesinde çeşitli öznitelik seçme yaklaşımlarının ve ön-işleme tekniğinin etkisi araştırıldı. Filtreleme aşamasında tüm öznitelik kümesi, kelime çantası (BoW = Bag of Words) modeliyle açığa çıkarılan özniteliklerden oluşturuldu. Kelime çantasındaki ayırt edici öznitelikler, öznitelik seçim yöntemleri kullanılarak belirlenir. Daha sonra SMS mesajlarını sınıflandırmak için yaygın olarak kullanılan sınıflandırma algoritmalarıyla beslenir. Filtreleme çerçevesi sadece Türkçe SMS veri kümesi üzerinde değerlendirildi. İlgili veri kümeleri üzerinde kapsamlı deneysel analiz, Multinomial Naïve Bayes(MNB) sınıflandırıcı ile EFS(Extensive Feature Selector) öznitelik seçim metotlarının kombinasyonlarının daha iyi sınıflandırma performansı sağladığını ortaya çıkardı. Kullanılan öznitelik seçim yöntemlerinin etkinliği, her sınıflandırıcıda biraz farklılık göstermektedir.

References

[1] Sjarif, N.N.A., et al., SMS Spam Message Detection using Term Frequency-Inverse Document Frequency and Random Forest Algorithm. Procedia Computer Science, 2019. 161: p. 509-515.

[2] Nagwani, N.K. and A. Sharaff, SMS spam filtering and thread identification using bi-level text classification and clustering techniques. Journal of Information Science, 2017. 43(1): p. 75-87.

[3] Karasoy, O. and S. Ballı. Classification Turkish SMS with deep learning tool Word2Vec. in 2017 International Conference on Computer Science and Engineering (UBMK). 2017. Ieee.

[4] Uysal, A.K., et al., The impact of feature extraction and selection on SMS spam filtering. Elektronika ir Elektrotechnika, 2013. 19(5): p. 67-72.

[5] Ballı, S. and O. Karasoy, Development of content‐based SMS classification application by using Word2Vec‐based feature extraction. IET Software, 2019. 13(4): p. 295-304.

[6] Karasoy, O. and S. Ballı, Spam SMS detection for Turkish language with deep text analysis and deep learning methods. Arabian Journal for Science and Engineering, 2021: p. 1-17.

[7] Uysal, A.K., et al. A novel framework for SMS spam filtering. in 2012 International Symposium on Innovations in Intelligent Systems and Applications. 2012. IEEE.

[8] Uysal, A.K., et al. Detection of SMS spam messages on mobile phones. in 2012 20th Signal Processing and Communications Applications Conference (SIU). 2012. Ieee.

[9] Uysal, A.K., et al., The impact of feature extraction and selection on SMS spam filtering. Elektronika ir Elektrotechnika, 2012. 19(5): p. 67-72.

[10] Parlak, B. and A.K. Uysal, The effects of globalisation techniques on feature selection for text classification. Journal of Information Science, 2020: p. 0165551520930897.

[11] Uysal, A.K. and S. Gunal, The impact of preprocessing on text classification. Information Processing & Management, 2014. 50(1): p. 104-112.

[12] Bhowmick, A. and S.M. Hazarika, E-Mail Spam Filtering: A Review of Techniques and Trends, in Advances in Electronics, Communication and Computing. 2018, Springer. p. 583-590.

[13] Venkatraman, S., B. Surendiran, and P.A.R. Kumar, Spam e-mail classification for the internet of things environment using semantic similarity approach. The Journal of Supercomputing, 2020. 76(2): p. 756-776.

[14] Roy, P.K., J.P. Singh, and S. Banerjee, Deep learning to filter SMS spam. Future Generation Computer Systems, 2020. 102: p. 524-533.

[15] Li, P., et al., Bag-of-Concepts representation for document classification based on automatic knowledge acquisition from probabilistic knowledge base. Knowledge-Based Systems, 2020. 193: p. 105436.

[16] Salton, G. and C. Buckley, Term-weighting approaches in automatic text retrieval. Information processing & management, 1988. 24(5): p. 513-523.

[17] Schütze, H., C.D. Manning, and P. Raghavan, Introduction to information retrieval. Vol. 39. 2008: Cambridge University Press.

[18] Al-Anzi, F.S. and D. AbuZeina, Beyond vector space model for hierarchical Arabic text classification: A Markov chain approach. Information Processing & Management, 2018. 54(1): p. 105-115.

[19] Akın, A.A. and M.D. Akın, Zemberek, an open source NLP framework for Turkic languages. Structure, 2007. 10: p. 1-5.

[20] Forman, G., An extensive empirical study of feature selection metrics for text classification. Journal of machine learning research, 2003. 3(Mar): p. 1289-1305.

[21] Singh, S.R., H.A. Murthy, and T.A. Gonsalves, Feature Selection for Text Classification Based on Gini Coefficient of Inequality. Fsdm, 2010. 10: p. 76-85.

[22] Rehman, A., K. Javed, and H.A. Babri, Feature selection based on a normalized difference measure for text classification. Information Processing & Management, 2017. 53(2): p. 473-489.

[23] Parlak, B. and A.K. Uysal, A novel filter feature selection method for text classification: Extensive Feature Selector. Journal of Information Science, 2021: p. 0165551521991037.

[24] Zhao, L., et al. Semi-supervised Multinomial Naive Bayes for text classification by leveraging word-level statistical constraint. in Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence. 2016. AAAI Press.

[25] Gabrilovich, E. and S. Markovitch. Text categorization with many redundant features: using aggressive feature selection to make SVMs competitive with C4. 5. in Proceedings of the twenty-first international conference on Machine learning. 2004. ACM.