Makine öğrenme algoritmalarını kullanan duygu tahminine dayalı müzik öneri sistemi
Yıl 2023,
Cilt: 18 Sayı: 68, 189 - 234, 30.12.2023
Hasan Alıyev
,
Peri Güneş
Öz
Müzik, insanlık tarihi boyunca duygusal ifadenin araçlarından biri olmuştur. Farklı kültürlerde farklı zaman dilimlerinde müzik bireylerin deneyimlerini duygularını anlatmanın eşsiz bir yolunu sunmuştur. Teknolojik ilerlemelerle birlikte müzikle etkileşimimizde büyük bir gelişme yaşanmış dijital platformlar sayesinde müziğe erişimimiz kolaylaşmıştır.
Geleneksel müzik öneri sistemleri kullanıcının müzik dinleme alışkanlıklarını baz alırken bu çalışma anlık duygu durumunu değerlendirerek müzik önerisi sunmayı hedeflemiştir. Kullandığımız model CNN temelli bir duygu tanıma sistemidir. Bu model yüz görüntülerini analiz ederek yedi duygudan birini tahmin eder. Modelin eğitim sürecinde Confusion Matrix sonuçları modelin duygu sınıflandırma konusunda iyi bir performans sergilediğini göstermektedir. ROC eğrisi analiz sonuçları modelin duyguyu tahmin etme kabiliyetinin yüksek olduğunu göstermektedir. Özellikle modelin genel doğruluk oranının %92,7 olması bu modelin ne kadar etkili olduğunu göstermektedir.
Bu çalışma, duyguya göre müzik öneri sistemlerinin kullanıcı deneyimini daha etkili bir hale getirme potansiyeline sahip olduğu görünmekte. Kullanıcının mevcut duygusunu analiz ederek, ona en uygun müzikleri önerme yeteneği müzik öneri sistemlerinin geleceğini şekillendirecek yenilikçi bir yaklaşım sunmaktadır.
Kaynakça
- De Prisco, R., et al. (2022). Induced Emotion-Based Music Recommendation
through Reinforcement Learning. Applied Sciences, 12(21), 11209.
- Martínez, J., & Vega, J. (2022). ROS System Facial Emotion Detection
Using Machine Learning for a Low-Cost Robot Based on Raspberry Pi.
Electronics, 12(1), 90.
- He, J. (2022). Algorithm Composition and Emotion Recognition Based
on Machine Learning. Computational Intelligence and Neuroscience.
- Ka, S., et al. (2021). Facial Emotion Based Music Recommendation
System Using Computer Vision and Machine Learning Techniques. Turkish
Journal of Computer and Mathematics Education, 12(1), 912-917.
- Koukaras, P., Nousi, C., & Tjortjis, C. (2022). Stock Market Prediction
Using Microblogging Sentiment Analysis and Machine Learning. Telecom,
3(2). MDPI.
- Rosa, R. L., Rodriguez, D. Z., & Bressan, G. (2015). Music Recommendation
System Based on User’s Sentiments Extracted from Social
Networks. IEEE Transactions on Consumer Electronics, 61(3), 359-367.
- Sashank, M. S. K., et al. (2022). Mood-Based Music Recommendation
System Using Facial Expression Recognition and Text Sentiment Analysis.
Journal of Theoretical and Applied Information Technology, 100(19).
- Chirasmayee, B. V. S., et al. (2022). Song Recommendation System
Using TF-IDF Vectorization and Sentimental Analysis.
- Mehta, R., & Gupta, S. (2021). Movie Recommendation Systems Using
Sentiment Analysis and Cosine Similarity. International Journal of Modern
Trends in Science and Technology, 7(01), 16-22.
- Düzbastılar, M. E., & Eyüpoğlu, G. (2019). Müzik Öğretmenlerinin
Özel Eğitime İhtiyacı Olan Öğrencilerin Müzik Öğretimine İlişkin Tutumlarının
İncelenmesi. International Journal of Social Sciences and Education
Research, 5(4), 384-404.
- Aydoğan, M., & Şener, A. (2020). Duygu Analizi Tabanlı Yeni Bir Hibrit
Tavsiyeci Sistem. Euroasia Journal of Mathematics, Engineering, Natural
& Medical Sciences, 7(13), 48-62.
- Gündüz, İ., & YILMAZ, Ö. (2021). Yüz İfadesini Algılayarak Kullanıcının
Ruh Haline Göre İçerik Öneren Mobil Uygulama. Avrupa Bilim ve
Teknoloji Dergisi, 28, 192-197.
- Yi, S., & Liu, X. (2020). Machine Learning Based Customer Sentiment Analysis for Recommending Shoppers, Shops Based on Customers’ Review. Complex & Intelligent Systems, 6(3), 621-634.
- Siam, A. I., et al. (2022). Deploying Machine Learning Techniques for
Human Emotion Detection. Computational Intelligence and Neuroscience.
- Wang, J., & Perez, L. (2017). The Effectiveness of Data Augmentation
in Image Classification Using Deep Learning.
- Parmigiani, G. (2020). Receiver Operating Characteristic Curves with
an Indeterminacy Zone. Pattern Recognition Letters, 136, 94-100.
- Qiu, H., & Jia, X. (2022). Western Music History Recommendation
System Based on Internet-of-Things Data Analysis Technology. Mobile
Information Systems, 2022, 8920599.
- Shorten, C., & Khoshgoftaar, T.M. (2019). A survey on Image Data
Augmentation for Deep Learning. Journal of Big Data, 6(1), 60.
- Masud, M. (2022). A light-weight convolutional Neural Network Architecture
for classification of COVID-19 chest X-Ray images. Multimedia
Systems, 28(4), 1165–1174.
- Nan, Y., Ju, J., Hua, Q., Zhan[g, H., & Wang, B. (2022). A-MobileNet:
An approach of facial expression recognition. Alexandria Engineering
Journal, 61(6), 4435-4444.
- Reyad, M., Sarhan, A., & Arafa, M. (2023). A modified Adam algorithm
for deep neural network optimization. Neural Computing & Applications,
35, 17095–17112.
- Düntsch, I., & Gediga, G. (2019). Confusion matrices and rough set
data analysis. In Proceedings of the 2019 International Conference on Pattern
Recognition and Intelligent Systems (PRIS 2019).
- Wu, M.T. (2022). Confusion matrix and minimum cross-entropy metrics
based motion recognition system in the classroom. Scientific Reports,
12, 3095.
- Görtler, J., Hohman, F., Moritz, D., Wongsuphasawat, K., Ren, D.,
Nair, R., Kirchner, M., & Patel, K. (2022). Neo: Generalizing Confusion
Matrix Visualization to Hierarchical and Multi-Output Labels. In CHI ‘22:
Proceedings of the 2022 CHI Conference on Human Factors in Computing
Systems (Article No. 408, pp. 1-13).
- Yik, M., Widen, S., & Russell, J. (2013). The within-subjects design in
the study of facial expressions. Cognition & Emotion, 27.
Music recommendation system based on Emotion Prediction using machine learning Algorithms
Yıl 2023,
Cilt: 18 Sayı: 68, 189 - 234, 30.12.2023
Hasan Alıyev
,
Peri Güneş
Öz
Music has been a means of emotional expression throughout human history. Different cultures and times have offered unique ways of expressing the emotions experienced by individuals through music. Technological advancements have greatly enhanced our interaction with music, making access easier thanks to digital platforms.
While traditional music recommendation systems are based on the user's listening habits, this study aims to provide music recommendations by evaluating the user's immediate emotional state. We utilize a CNN-based emotion recognition system for this purpose. This model predicts one of seven emotions by analyzing facial images. The results of the Confusion Matrix in the training phase indicate that the model is proficient at classifying emotions. ROC curve analysis shows the model's high capability in emotion prediction. Notably, the model's overall accuracy stands at 92.7%, highlighting its effectiveness.
This research demonstrates the potential of emotion-based music recommendation systems in enhancing the user experience. The capacity to recommend the most fitting music by gauging the user's current emotional state presents an innovative approach that may shape the future of music recommendation systems.
Kaynakça
- De Prisco, R., et al. (2022). Induced Emotion-Based Music Recommendation
through Reinforcement Learning. Applied Sciences, 12(21), 11209.
- Martínez, J., & Vega, J. (2022). ROS System Facial Emotion Detection
Using Machine Learning for a Low-Cost Robot Based on Raspberry Pi.
Electronics, 12(1), 90.
- He, J. (2022). Algorithm Composition and Emotion Recognition Based
on Machine Learning. Computational Intelligence and Neuroscience.
- Ka, S., et al. (2021). Facial Emotion Based Music Recommendation
System Using Computer Vision and Machine Learning Techniques. Turkish
Journal of Computer and Mathematics Education, 12(1), 912-917.
- Koukaras, P., Nousi, C., & Tjortjis, C. (2022). Stock Market Prediction
Using Microblogging Sentiment Analysis and Machine Learning. Telecom,
3(2). MDPI.
- Rosa, R. L., Rodriguez, D. Z., & Bressan, G. (2015). Music Recommendation
System Based on User’s Sentiments Extracted from Social
Networks. IEEE Transactions on Consumer Electronics, 61(3), 359-367.
- Sashank, M. S. K., et al. (2022). Mood-Based Music Recommendation
System Using Facial Expression Recognition and Text Sentiment Analysis.
Journal of Theoretical and Applied Information Technology, 100(19).
- Chirasmayee, B. V. S., et al. (2022). Song Recommendation System
Using TF-IDF Vectorization and Sentimental Analysis.
- Mehta, R., & Gupta, S. (2021). Movie Recommendation Systems Using
Sentiment Analysis and Cosine Similarity. International Journal of Modern
Trends in Science and Technology, 7(01), 16-22.
- Düzbastılar, M. E., & Eyüpoğlu, G. (2019). Müzik Öğretmenlerinin
Özel Eğitime İhtiyacı Olan Öğrencilerin Müzik Öğretimine İlişkin Tutumlarının
İncelenmesi. International Journal of Social Sciences and Education
Research, 5(4), 384-404.
- Aydoğan, M., & Şener, A. (2020). Duygu Analizi Tabanlı Yeni Bir Hibrit
Tavsiyeci Sistem. Euroasia Journal of Mathematics, Engineering, Natural
& Medical Sciences, 7(13), 48-62.
- Gündüz, İ., & YILMAZ, Ö. (2021). Yüz İfadesini Algılayarak Kullanıcının
Ruh Haline Göre İçerik Öneren Mobil Uygulama. Avrupa Bilim ve
Teknoloji Dergisi, 28, 192-197.
- Yi, S., & Liu, X. (2020). Machine Learning Based Customer Sentiment Analysis for Recommending Shoppers, Shops Based on Customers’ Review. Complex & Intelligent Systems, 6(3), 621-634.
- Siam, A. I., et al. (2022). Deploying Machine Learning Techniques for
Human Emotion Detection. Computational Intelligence and Neuroscience.
- Wang, J., & Perez, L. (2017). The Effectiveness of Data Augmentation
in Image Classification Using Deep Learning.
- Parmigiani, G. (2020). Receiver Operating Characteristic Curves with
an Indeterminacy Zone. Pattern Recognition Letters, 136, 94-100.
- Qiu, H., & Jia, X. (2022). Western Music History Recommendation
System Based on Internet-of-Things Data Analysis Technology. Mobile
Information Systems, 2022, 8920599.
- Shorten, C., & Khoshgoftaar, T.M. (2019). A survey on Image Data
Augmentation for Deep Learning. Journal of Big Data, 6(1), 60.
- Masud, M. (2022). A light-weight convolutional Neural Network Architecture
for classification of COVID-19 chest X-Ray images. Multimedia
Systems, 28(4), 1165–1174.
- Nan, Y., Ju, J., Hua, Q., Zhan[g, H., & Wang, B. (2022). A-MobileNet:
An approach of facial expression recognition. Alexandria Engineering
Journal, 61(6), 4435-4444.
- Reyad, M., Sarhan, A., & Arafa, M. (2023). A modified Adam algorithm
for deep neural network optimization. Neural Computing & Applications,
35, 17095–17112.
- Düntsch, I., & Gediga, G. (2019). Confusion matrices and rough set
data analysis. In Proceedings of the 2019 International Conference on Pattern
Recognition and Intelligent Systems (PRIS 2019).
- Wu, M.T. (2022). Confusion matrix and minimum cross-entropy metrics
based motion recognition system in the classroom. Scientific Reports,
12, 3095.
- Görtler, J., Hohman, F., Moritz, D., Wongsuphasawat, K., Ren, D.,
Nair, R., Kirchner, M., & Patel, K. (2022). Neo: Generalizing Confusion
Matrix Visualization to Hierarchical and Multi-Output Labels. In CHI ‘22:
Proceedings of the 2022 CHI Conference on Human Factors in Computing
Systems (Article No. 408, pp. 1-13).
- Yik, M., Widen, S., & Russell, J. (2013). The within-subjects design in
the study of facial expressions. Cognition & Emotion, 27.