Müzik Veri Setinin Analizi ve Sınıflandırma Algoritmaları Kullanılarak Şarkı Türü Tahminleme Çalışması

Yıl 2022, Sayı: 40, 143 - 150, 30.09.2022

Berke Bartuğ Sevindik Vahide Bulut

https://doi.org/10.31590/ejosat.1174115

Öz

Bu araştırmanın amacı, Spotify müzik platformunda yer alan 42305 şarkı ve 15 farklı türe sahip veri setini analiz edip şarkının
türlerle olan ilişkisini incelemektir. Bu türlerle olan ilişkiler veri setinden tür tahminleme çalışması için ön değerlendirme olarak analiz
edilmiştir. Veri setindeki türlere ait özellikler değerlendirilip, kategorik olarak özelliklerine göre veri madenciliği sınıflandırma
algoritmalarından; En yakın K-Komşu, rastgele orman, torbalama ve lojistik regresyon kullanılmıştır. Şarkının özelliklerine göre
şarkıların türlerini tahmin etme çalışması gerçekleştirilmiştir. %55 ve %77 arasında doğruluk değerleri elde edilmiştir. Sınıflandırma
algoritmalarının en iyi performans ölçüm değerine sahip bir model ele alınarak sonuçları değerlendirilmiştir.

Anahtar Kelimeler

Tahminleme, Analiz, En yakın k-komşu, Rasgele orman, torbalama, Lojistik regresyon, Sınıflandırma algoritmaları

Song Genre Estimation Study Using Music Data Set Analysis and Classification Algorithms

Öz

The aim of this research is to analyze the dataset of 42305 songs and 15 different genres on the Spotify music platform and examine the relationship of the song with the genres. Relationships with these species were analyzed from the dataset as a preliminary assessment for the species prediction study. The features of the species in the data set are evaluated and categorically according to their features, from data mining classification algorithms; Nearest K-Neighbor, random forest, bagging and logistic regression were used. The study was carried out to predict the types of songs according to the characteristics of the song. Accuracy values between 55% and 77% were obtained. A model with the best performance measurement value of the classification algorithms was considered and the results were evaluated.

Anahtar Kelimeler

Prediction, Analysis, K-nearest k-neighbors, Random forest, Logistic regression, bagging, Classification algorithms

Kaynakça

• Sklearn.svm.LinearSVC. scikit. (n.d.). Retrieved September 11, 2022, from https://scikitlearn.org/stable/modules/generated/sklearn.svm.LinearSVC .html
• About Spotify. Spotify. (2022, July 27). Retrieved September 11, 2022, from https://newsroom.spotify.com/companyinfo/.
• Mavuduru, A. (2021, February 10). How to build an amazing music recommendation system. Medium. Retrieved September 11, 2022, from https://towardsdatascience.com/how-to-build-an-amazingmusic-recommendation-system-4cce2719a572
• T., Tibshirani, R. & Friedman, J. (2008). The Elements of Statictical Learning: Data Mining, Inference, and Prediction, Second Edition, Springer.
• Rajavarman, V.N. ; Rajagopalan, S.P. ; Comparison between Traditional data mining Techniques and Entropy-based Adaptive Genetic Algorithm for Learning Classification Rules; International Journal of Soft Computing Vol 2 Issue 4; 2007; 555-561.
• Öztemel, E. (2012). Yapay sinir ağları. (3.baskı). İstanbul: Papatya Yayıncılık.
• Han, J., Kamber, M. and Pei, J. (2012). Data mining: Concepts and techniques. (3rd Edition). Waltham: Morgan Kaufmann.
• J. Khairnar and M. Kinikar, “Machine learning algorithms for opinion mining and sentiment classification,” International Journal of Scientific and Research Publications, vol. 3, no. 6, pp. 1–6, 2013.
• N. Mishra and C. K. Jha, “Classification of opinion mining techniques,” International Journal of Computer Applications, vol. 56, no. 13, pp. 1–6, 2012.
• Watts JD, Lawrence RL. 2008. Merging random forest classification with an object-oriented approach for analysisof agricultural lands, The International Archives of the Photogrammetry, Remote Sensing and Spatial InformationSciences, XXXVII(B7)
• Loh WY, Shih YS. 1997. Split selection methods for classification trees. Statistica Sinica 7: 815-840.
• Wang, C., Long, Y., Li, W. et al. (2020). Exploratory study on classification of lung cancer subtypes through a combined K-nearest neighbor classifer in breathomics. Sci Rep, 3;10(1):5880. doi:10.1038/s41598-020-62803-4.
• ULUSLARARASI SAĞLIK YÖNETİMİ VE STRATEJİLERİ ARAŞTIRMA DERGİSİ http://dergipark.gov.tr/usaysad (VERANYURT, Ü /DEVECİ, AF /ESEN, MF /VERANYURT
• Mercaldo, F., Nardone, V., Santone, A. (2017). Diabetes Mellitus Affected Patients Classification and Diagnosis through Machine Learning Techniques. Procedia Computer Science, 112: 2519-228.
• Mujumdar, A., Vaidehi, V. (2019). Dibetes Prediction Using Machine Learning Algorithms. Procedia Computer Science, 165: 292–299.
• Cover, T. and Hart, P. (1967). Nearest neighbor pattern classification,"Information Theory, IEEE Transactions, 13: 21-27.
• Breiman, L. (2001). Random forest. Mach. Learn, 45: 5–32. doi: 10.1023/A:1010933404324.
• “Analysis of Top Tracks in Spotify.” Https://Web.stanford.edu/, 25 Oct. 2018, web.stanford.edu/~kjytay/courses/stats32- aut2018/Session%208/Spotify_final.html.
• Ay, Yamac Eren. “Spotify Dataset 1921-2020, 160k+Tracks.” Kaggle, 24 Jan. 2021, www.kaggle.com/yamaerenay/spotify-dataset-19212020-160k-tracks.
• Alpaydın, E., 2014, Introduction to Machine Learning, MIT Press, ISBN: 978-0-262-02818-9.
• Alpaydın, E., 2006, Projects in Machine Learning, http://web.eecs.utk.edu/~parker/Courses/CS594spring06/handouts/Introduction.pdf
• Harrington, P., 2012, Machine Learning in Action, 1st Edition, Manning Publications Shelter Island, NY, ISBN:978-1-61729-018-3.
• Ölçü ve ölçü çizgisi nedir, ölçü işareti Nedir. Eğitim Sistem. (n.d.). Retrieved September 11, 2022, from https://www.egitimsistem.com/olcu-isareti-nedir-86365h.htm
• Gürsakal, N. (2001) Sosyal Bilimlerde Araştırma Yöntemleri, Uludağ Üniversitesi Basımevi, Bursa.
• Gürsakal, N. (2007) Betimsel İstatistik Minitab, Spss, Statistica, Excel Uygulamalı, Nobel Yayın Dağıtım, Ankara.
• Akpınar, H. (2000) “Veri Tabanlarında Bilgi Keşfi ve Veri Madenciliği”, İstanbul Üniversitesi İşletme Fakültesi Dergisi, Cilt 29, Sayı 1/Nisan, s. 1–22.
• Yıldırım, P., Uludağ, M. ve Görür, A. (2007), “Hastane Bilgi Sistemlerinde Veri Madenciliği”, Akademik Bilişim Kongresi, Çanakkale Onsekiz MartÜniversitesi, Çanakkale, 30 Ocak-1 Şubat 2007.
• Ganesh, S. (2002) “Data Mining: Should it be included in the ‘Statistics’ cirriculum?”, The Sixt International Conference on Teaching Statistics, Cape Town, South Africa, 7–12 July.
• Koyuncugil, A. S. (2007) “Veri Madenciliği ve Sermaye Piyasalarına Uygulaması”, Sermaye Piyasası Kurulu Araştırma Raporu, Araştırma Dairesi, 28.02.2007 ASK/1
• Santos, J. D. D. (2017, May 31). Is my Spotify music boring? an analysis involving music, data, and machine learning. Medium. Retrieved September 11, 2022, from https://towardsdatascience.com/is-my-spotify-musicboring-an-analysis-involving-music-data-and-machinelearning-47550ae931de
• Ay, Şevket. (2019, December 16). Ensemble learning - bagging VE boosting. Medium. Retrieved September 11, 2022, from https://medium.com/deep-learningturkiye/ensemble-learning-bagging-ve-boosting-50643428b22b