350 rub
Journal Nonlinear World №2 for 2025 г.
Article in number:
Machine learning model for musical emotion classification in recommender systems
Type of article: scientific article
DOI: https://doi.org/10.18127/j20700970-202502-03
UDC: 004.032.26, 303.732.4
Keywords: Neural network machine learning classification musical emotion recognition stacking multilayer perceptron decision tree support vector method bagging spectrogram
Authors:

D.V. Plaksin1, T.E. Badokina2, E.V. Shchennikova3

1–3 Federal State Budgetary Educational Institution of Higher Education “National Research Mordovia State University” (Saransk, Russia)
1dmitriy.plaksin1@yandex.ru; 2badokinate@math.mrsu.ru; 3schennikova8000@yandex.ru

Abstract:

The problem of classifying musical emotions arises when building recommendation systems for creating mood-based playlists. However, existing methods for classifying musical emotions do not always provide sufficient accuracy. This creates a need for the development of more effective methods and models, as many modern online music services strive to personalize content using recommendation systems, including the creation of mood-based playlists. To form such playlists, it is necessary to first solve the problem of recognizing the emotional tone of musical compositions based on their lyrics and audio features, which is a task related to the field of information management and processing. The aim of the article is to develop a machine learning model that improves the quality of musical emotion prediction based on the analysis of known and current methods and models.

During the research, methods for extracting characteristics from musical compositions and techniques for organizing architecture to solve the problem were analyzed. An ensemble architecture and machine learning model based on stacking algorithms, multilayer perceptrons (with a ReLU activation function), decision trees, and bagging were developed for classifying musical emotions. A comparative analysis using the F-measure metric was conducted with alternative approaches on the same dataset.

The developed model can be used in music recommendation systems for automatically creating mood-based playlists, improving user experience and the quality of personalized music services.

Pages: 22-31
For citation

Plaksin D.V., Badokina T.E., Shchennikova E.V. Machine learning model for musical emotion classification in recommender systems. Nonlinear World. 2025. V. 23. № 2. P. 22–31. DOI: https:// doi.org/10.18127/ j20700970-202501-03 (In Russian)

References
  1. Yang Y.-H., Chen H.H. Music Emotion Recognition. CRC Press. 2011. 262 p.
  2. Plaksin D.V. Primenenie nejrosetevyh tekhnologij pri proektirovanii rekomendatel'nyh sistem v muzykal'nyh onlajn-servisah. Materialy XXV nauch.-prakt. konf. molodyh uchenyh, aspirantov i studentov Nacional'nogo issledovatel'skogo Mordovskogo gosudarstvennogo universiteta. V 3-h chastyah. Saransk. 2022. T. 2. S. 349–354 (In Russian).
  3. Katayose H., Imai M., Inokuchi S. Sentiment extraction in music. Proceedings of the International Conference on Engineering and Telecommunication. Rome. 1988. V. 2. R. 1083–1087.
  4. Feng Y., Zhuang Y., Pan Y. Popular Music Retrieval by Detecting Mood. Proceedings of the 26th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. Toronto. 2003. P. 375–376.
  5. Lu L., Liu D., Jang H.-J. Automatic mood detection and tracking of music audio signal. IEEE Transactions on Audio, Speech, and Language Processing. 2006. V. 14. № 1. P. 5–18.
  6. Sujeesha S., Rajan R. Transformer-based Automatic Music Mood Classification Using Multi-modal Framework. Journal of Computer Science and Technology. 2023. V. 23. P. 18–34.
  7. Xiaoguang J. Music Emotion Classification Method Based on Deep Learning and Improved Attention Mechanism. Computational Intelligence and Neuroscience. 2022.
  8. Rajesh S., Nalini N.J. Musical instrument emotion recognition using deep recurrent neural network. Procedia Computer Science. 2020. V. 167. P. 16–25.
  9. Han X., Chen F, Ban J. Music Emotion Recognition Based on a Neural Network with an Inception-GRU Residual Structure. Electronics. 2023. V. 12. № 4.
  10. AudioSet [Elektronnyj resurs] URL= https://research.google.com/audioset/dataset/soundtrack_music.html (data obrashcheniya: 02.07.2024).
  11. Wang W. CNN based music emotion recognition. 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE). Hangzhou. 2021. P. 190-195.
  12. Hizlisoy S., Yildirim S., Tufekci Z. Music emotion recognition using convolutional long short term memory deep neural networks. Engineering Science and Technology. 2021. V. 24. № 3. P. 760-767.
  13. Music Information Retrieval CISUC [Elektronnyj resurs] URL= http://mir.dei.uc.pt/downloads.html (data obrashcheniya: 04.07.2024).
  14. Mukkamal J., Radhika Y. A Review: Music Feature Extraction from an Audio Signal. International Journal of Advanced Trends in Computer Science and Engineering. 2020. V. 9. № 2. P. 973–980.
  15. Nefedov V.I., Pugachev O.I., Egorova E.V., Gerasimov A.V. Primenenie cifrovoj obrabotki dlya fil'tracii shuma v zvukovyh signalah. Nelinejnyj mir. 2009. T. 7. № 11. S. 869–871 (In Russian).
  16. Shchennikova, E.V., Flerina D.Yu., Navoshin R.E. Preprocessing rechevyh dannyh s cel'yu obucheniya nejronnoj seti. Inzhenernyj vestnik Dona. 2023. T. 105. № 9. S. 192–200 (In Russian).
  17. Russell J.A. A Circumplex Model of Affect. Journal of Personality and Social Psychology. 1980. V. 39. P. 1161–1178.
  18. Thayer R.E. The Biopsychology of Mood and Arousal. Oxford University Press. 1989. 247 p.
  19. Importance of Feature Scaling – scikit-learn 1.5.1 documentation [Elektronnyj resurs] URL= https://scikit-learn.org/stable/auto_ examples/preprocessing/plot_scaling_importance.html (data obrashcheniya: 04.07.2024).
  20. 6.3. Preprocessing data – scikit-learn 1.5.1 documentation [Elektronnyj resurs] URL= https://scikit-learn.org/stable/modules/ preprocessing.html#normalization (data obrashcheniya: 04.07.2024).
  21. Wolpert D. Stacked Generalization. Neural Networks. 1992. V 5. P. 241–259.
  22. Popescu M.-C., Balas V., Perescu-Popescu L., Mastorakis N. Multilayer perceptron and neural networks. WSEAS Transactions on Circuits and Systems. 2009. V 8. P. 579–588.
  23. Chesalin A.N. Primenenie kaskadnyh algoritmov klassifikacii dlya sovershenstvovaniya sistem obnaruzheniya vtorzhenij. Nelinejnyj mir. 2022. T. 20. № 1. S. 24–41 (In Russian).
  24. Theodoros E., Massimiliano P. Support Vector Machines: Theory and Applications. Machine Learning and Its Applications, Advanced Lectures. V. 2049. P. 249–257.
  25. Dvojris L.I., Gerashchenkov V.A. Podbor parametrov yadra i parametra metoda dlya nelinejnyh klassifikatorov. Radiotekhnika. 2013. № 2. S. 83–86 (In Russian).
  26. Breiman L. Bagging predictors. Machine Learninig. 1996. V. 24. P. 123–140.
  27. Badokina T.E., Lizina O.M. Ispol'zovanie mnogofaktornogo analiza pri vyyavlenii determinant rossijskoj tenevoj ekonomiki. Russian Economic Bulletin. 2019. T. 2. № 5. S. 67–72 (In Russian).
  28. Hand D.J., Christen P., Kirielle N. F*: an interpretable transformation of the F-measure. Mach Learn. 2021. V. 110. P. 451–456.
  29. Er M. B., Esi E. M. Music Emotion Recognition with Machine Learning Based on Audio Features. Computer Science. 2021. V. 6. № 3. P. 133–144.
  30. Panda R., Malheiro R., Paiva R.P. Novel Audio Features for Music Emotion Recognition. Transactions on Affective Computing. 2018. V. 11. № 4. P. 614–626.
  31. Koh E., Dubnov, S. Comparison and analysis of deep audio embeddings for music emotion recognition. CEUR Workshop Proceedings. V. 2897. P. 15–22.
Date of receipt: 12.03.2025
Approved after review: 21.03.2025
Accepted for publication: 29.04.2025