Basic Search / Detailed Display

Author: Glleen Allan Marchellim
Glleen Allan Marchellim
Thesis Title: Music Visualization of Content-Based Artist Recommendation
Music Visualization of Content-Based Artist Recommendation
Advisor: 楊傳凱
Chuan-Kai Yang
Committee: 羅乃維
Nai-Wei Lo
林伯慎
Bor-Shen Lin
Degree: 碩士
Master
Department: 管理學院 - 資訊管理系
Department of Information Management
Thesis Publication Year: 2021
Graduation Academic Year: 109
Language: 英文
Pages: 63
Keywords (in Chinese): Music VisualizationMusic Recommender SystemK-Nearest NeighborsK-NNCosine
Keywords (in other languages): Music Visualization, Music Recommender System, K-Nearest Neighbors, K-NN, Cosine
Reference times: Clicks: 223Downloads: 5
Share:
School Collection Retrieve National Library Collection Retrieve Error Report


There are over 10 million tracks stored at music streaming platform. Music visualization research could provide a great help for the music industry to know their users, their desired content, and to know what can be done to improve the platforms. With a lot of music or songs being produced every year, it is quite difficult to listen to all those songs. A recommender system will help a user get information of a new song that can be similar to what they have heard and will help a new released song to reach an end user sooner so that the song can become popular. This research develops a web-based application that can visualize data of music using D3.js and gives a recommendation based on a user’s preference using K-NN and cosine similarity methods. The dataset used for this research is collected from Spotify on November 1st, 2020, consisting of 169,910 tracks and 27,621 artists from 1920-2020.
Our system shows that for the visualization results using Spotify dataset, the more era closer to the current year, the more song considered as popular from Spotify and has more similarity on each song but affects to the visualization time will took longer and the aesthetic aspect will be resulting a messy visualization since the more nodes and links need to be visualized. On the artist recommendation experiments, K-NN offers better performance for both experiment using artists of the same genre as the input and using artists with different genres as the input. On both experiments, K-NN offers more relevant artist results while cosine similarity still could provide some irrelevant artists. The better result and output using K-NN leading the system to visualizes more nodes and more similarity links on each node.

Master’s Thesis Recommendation Form I Qualification Form by Master’s Degree Examination Committee II Abstract III Acknowledgment IV Table of Contents V List of Figures VII List of Tables IX Chapter 1. Introduction 1 1.1 Background 1 1.2 Contribution 3 1.3 Research Outline 3 Chapter 2. Related Works 5 2.1 Graph 5 2.1.1 Force-Directed Graph 6 2.2 Music Data Visualization 7 2.3 Music Recommender System 11 2.4 Recommender System Using K-NN 13 Chapter 3. Proposed System 15 3.1 System Overview 15 3.2 System Architecture 18 3.3 Dataset 20 3.4 Similarity Calculation 22 3.5 Recommendation System 24 Chapter 4. Experimental Results 27 4.1 Experimental Parameters 27 4.2 Experimental Results 30 4.2.1 Music Visualization Result 30 4.2.2 Artist Recommender Result 36 Chapter 5. Conclusion and Future Work 48 5.1 Conclusion 48 5.2 Limitation and Future Work 49 References 50

[1] L. Barrington, R. Oda and G. Lanckriet, “Smarter than Genius? Human Evaluation of Music Recommender Systems,” 10th International Society for Music Information Retrieval Conference (ISMIR 2009), pp. 357-362, 2009.
[2] H. Han, X. Luo, T. Yang and Y. Shi, “Music Recommendation Based on Feature Similarity,” 2018 IEEE International Conference of Safety Produce Informatization (IICSPI), pp. 650-654, 2018.
[3] M. Friendly, “A Brief History of Data Visualization,” in Handbook of data visualization, Springer, 2008, pp. 15-56.
[4] J. Zhou, Y. Fan and J. Zhang, “Generating Knowledge Maps for Songs and Users in Music Market with Probabilistic Topic Model,” 2019 IEEE Fifth International Conference on Big Data Computing Service and Applications (BigDataService), pp. 83-92, 2019.
[5] W. T. Tutte, “How to draw a graph,” Proceedings of the London mathematical, pp. 743-768, 1963.
[6] P. Eades, “A heuristic for graph drawing,” Proc. of the 13th Manitoba Conference on Numerical Mathematics and Computing, vol. 24, 1984.
[7] T. Kamada and S. Kawai, “An algorithm for drawing general undirected graphs,” Information Processing Letters, vol. 31, no. 1, pp. 7-15, 1989.
[8] T. M. J. Fruchterman and E. M. Reingold, “Graph drawing by force‐directed placement,” Software: Practice and Experience, vol. 21, no. 11, pp. 1129-1164, 1991.
[9] G. D. Battista, P. Eades, R. Tamassia and I. G. Tollis, Graph drawing : algorithms for the visualization of graphs, Upper Saddle River NJ: Prentice-Hall, 1999.
[10] M. Wattenberg, “Arc Diagrams: Visualizing Structure in Strings,” Proceedings of the IEEE Symposium on Information Visualization 2002 (InfoVis’02), pp. 110-116, 2002.
[11] C. S. Sapp, “Harmonic Visualizations of Tonal Music,” ICMC, pp. 419-422, 2001.
[12] A. Rodrigues, A. Cardoso and P. Machado, “Harmonic Constellation: An Audiovisual Environment of Living Organisms,” MUME 2016 - The Fourth International Workshop on Musical Metacreation, 2016.
[13] G. D. Cantareira, L. G. Nonato and F. V. Paulovich, “MoshViz: A Detail+Overview Approach to Visualize Music Elements,” IEEE TRANSACTIONS ON MULTIMEDIA, vol. 18, no. 11, pp. 2238-2246, 2016.
[14] J. Lee, G. Noh and C.-k. Kim, “Analysis & Visualization on movie’s popularity and reviews,” 2014 International Conference on Big Data and Smart Computing (BIGCOMP), pp. 189-190, 2014.
[15] M. Ribeiro, C. Prandi, V. Nisi and N. Nunes, “A data visualization interactive exploration of human mobility data during the COVID-19 outbreak: a case study,” 2020 IEEE Symposium on Computers and Communications (ISCC), pp. 1-6, 2020.
[16] J. B. Schafer, D. Frankowski, J. Herlocker and S. Sen, “Collaborative Filtering Recommender Systems,” in The Adaptive Web, Berlin, Heidelberg, Springer, 2007, pp. 291-324.
[17] M. J. Pazzani and D. Billsus, “Content-Based Recommendation Systems,” in The Adaptive Web, Berlin, Heidelberg, Springer, 2007, pp. 325-341.
[18] K. Tada, R. Yamanishi and S. Kato, “Interactive Music Recommendation System for Adapting Personal Affection: IMRAPA,” International Conference on Entertainment Computing, pp. 417-420, 2012.
[19] E. Shakirova, “Collaborative Filtering for Music Recommender System,” IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (EIConRus), pp. 548-550, 2017.
[20] J. Foote, “An overview of audio information retrieval,” Multimedia Systems, vol. 7, pp. 2-10, 1999.
[21] A. Wang, “An Industrial Strength Audio Search Algorithm,” 4th International Conference on Music Information Retrieval, pp. 27-30, 2003.
[22] P. Hoffman, A. Kaczmarek, P. Spaleniak and B. Kostek, “Music recommendation system,” Journal of Telecommunications and Information Technology, pp. 59-69, 2014.
[23] B. Li, Q. Tao and X. Li, “Music feature extraction based on fractal dimension theory for music recommendation system,” 5th International Conference on Measurement, Instrumentation and Automation, pp. 538-542, 2016.
[24] X. Luo, X. Liu, R. Tao and Y. Shi, “Content-based retrieval of music using mel frequency cepstral coefficient ( MFCC ),” Computer Modelling & New Technologies, pp. 1356-1361, 2014.
[25] M. Soleymani, A. Aljanaki, F. Wiering and R. C. Veltkamp, “Content-based music recommendation using underlying music preference structure,” 2015 IEEE International Conference on Multimedia and Expo (ICME), pp. 1-6, 2015.
[26] E. Fix and J. L. Hodges, “Discriminatory Analysis. Nonparametric Discrimination: Consistency Properties,” USAF School of Aviation Medicine, Texas, 1951.
[27] N. S. Altman, “An introduction to kernel and nearest-neighbor nonparametric regression,” The American Statistician, vol. 46, no. 3, pp. 175-185, 1992.
[28] W. T. H. Putri, M. S. Prastio, R. Hendrowati, Y. Sari and H. T. Y. Achsan, “Content-based Filtering Model for Recommendation of Indonesian Legal Article Study Case of Klinik Hukumonline,” 2019 International Workshop on Big Data and Information Security (IWBIS), pp. 9-14, 2019.
[29] B. Li, S. Wan, H. Xia and F. Qian, “The Research for Recommendation System Based on Improved KNN Algorithm,” 2020 IEEE International Conference on Advances in Electrical Engineering and Computer Applications (AEECA), pp. 796-798, 2020.
[30] G. Li and J. Zhang, “Music personalized recommendation system based on improved KNN algorithm,” 2018 IEEE 3rd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC 2018), pp. 777-781, 2018.
[31] “Spotify Dataset 1921-2020, 160k+ Tracks,” [Online]. Available: https://www.kaggle.com/yamaerenay/spotify-dataset-19212020-160k-tracks. [Accessed 1 November 2020].
[32] Spotify Technology S.A., “Spotify - Company Info,” Spotify Technology S.A., 31 December 2020. [Online]. Available: https://newsroom.spotify.com/company-info/. [Accessed 24 March 2021].
[33] J. Crnic, “Introduction to Modern Information Retrieval,” Library Management, vol. 32, pp. 373-374, 2011.
[34] B. G. Batchelor, Pattern recognition: ideas in practice, Berlin, Heidelberg: Plenum Press, 1978.
[35] R. S. Michalski, R. E. Stepp and E. Diday, “A recent advance in data analysis: clustering objects into classes characterized by conjunctive concepts,” Progress in pattern recognition, pp. 33-56, 1981.
[36] J. Beckwith, “The Evolution of Music Genre Popularity,” The DataFace, 7 September 2016. [Online]. Available: https://thedataface.com/2016/09/culture/genre-lifecycles. [Accessed 4 July 2021].
[37] Spotify Technology S.A., “The Trends That Shaped Streaming in 2020,” Spotify Technology S.A., 1 December 2020. [Online]. Available: https://newsroom.spotify.com/2020-12-01/the-trends-that-shaped-streaming-in-2020/. [Accessed 4 July 2021].
[38] Statista, “Share of Spotify users in the United States as of March 2018, by age,” Statista, March 2018. [Online]. Available: https://www.statista.com/statistics/475821/spotify-users-age-usa/. [Accessed 4 July 2021].

QR CODE