Music Recommendation Based on Subjective Attributes

Authors

  • Jain P Department of Computer Engineering, Veermata Jijabai Technological Institute (VJTI), Mumbai, Maharashtra, India
  • Patchava V Department of Electronics & Communication Engineering, RGUKT-Nuzvid, Andhra Pradesh, India

Keywords:

Music, Recommendation, Euclidean Distance, Machine Learning, Content-Based Filtering, Echonest, Danceability

Abstract

Majority of the music recommendation systems in use today use historical preferences of other users having similar taste to recommend songs to a particular user. Other systems use past preferences of the current user and musical attributes of songs to make recommendations. In this paper, we use a novel approach to recommend music to users based on content-based filtering. This system can be used both as a search engine and for making recommendations. Moreover, this system does not suffer from the cold start problem which most of the recommender systems suffer from. Our system has a very small learning curve. We present a simple yet fast approach to make music recommendations using echonest’s music attributes. The system is based on calculating the Euclidean distance to find out top recommended songs. This system can be used in combination with traditional recommendation systems for more effective recommendation. We think music users will find this system easy to use and experiment with and therefore helpful to discover new music. This system will result in increased enjoyment of music for users.

References

Spotify, music for everyone. https://www.spotify.com, Aug 2015

Collaborative Filtering at Spotify, slide 4 of 63. http://www.slideshare.net/erikbern/collaborative-filtering-at-spotify-16182818, Aug 2015

Pandora Internet Radio, listen to free music you’ll love. http://www.pandora.com, Aug 2015

Michael Howe. “Pandora’s Music Recommender”. http://courses.cs.washington.edu/courses/csep521/07wi/prj/michael.pdf

Thierry Bertin-Mahieux, Daniel P.W. Ellis, Brian Whitman, and Paul Lamere. The Million Song Dataset. In Proceedings of the 12th International Society for Music Information Retrieval Conference (ISMIR 2011), 2011.

Echonest. http://developer.echonest.com/docs/v4, Sep 2015

Acoustic Attributes, The Echo Nest Developer Center. http://developer.echonest.com/acoustic-attributes.html, Sep 2015

Danceability and Energy: Introducing Echo Nest. http://runningwithdata.com/post/1321504427/danceability-and-energy, Sep 2015

Downloads

Published

2025-11-10

How to Cite

[1]
P. Jain and V. Patchava, “Music Recommendation Based on Subjective Attributes”, Int. J. Comp. Sci. Eng., vol. 3, no. 10, pp. 80–91, Nov. 2025.

Issue

Vol. 3 No. 10 (2015): IJCSE October Edition

Section

Review Article

License

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.