INNS 2016: Advances in Big Data pp 179-185 | Cite as

Playlist Generation via Vector Representation of Songs

Conference paper
First Online:
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 529)

Abstract

This study proposes a song recommender system. The architecture is based on a distributed scalable big data framework. The recommender system analyzes songs a person listens to most and recommends a list of songs as a playlist. To realize the system, we use Word2vec algorithm by creating vector representations of songs. Word2vec algorithm is adapted to Apache Spark big data framework and run on distributed vector representation of songs to produce a playlist reflecting a person’s personal tastes. The performance results are evaluated in terms of hit rates at the end of the paper.

Keywords

Playlist generation Word2vec Word embedding Music recommendation retrieval 
This is a preview of subscription content, log in to check access.

References

  1. 1.
    Bobadilla, J., Ortega, F., Hernando, A., Gutiérrez, A.: Recommender systems survey. Knowl. Based Syst. 46, 109–132 (2013)CrossRefGoogle Scholar
  2. 2.
    Celma, O.: Music Recommendation. Springer, Berlin, Heidelberg (2012)MATHGoogle Scholar
  3. 3.
    Levy, M., Sandler, M.: Music information retrieval using social tags and audio. IEEE Trans. Multimedia 11, 383–395 (2009)CrossRefGoogle Scholar
  4. 4.
    Knees, P., Pohle, T., Schedl, M., Schnitzer, D., Seyerlehner, K.: A document-centered approach to a natural language music search engine. Adv. Inf. Retr. 4956, 627–631 (2008)Google Scholar
  5. 5.
    Logan, B.: Content-based playlist generation: exploratory experiments. In: Processing of 3rd International Conference on Music Information Retrieval, Paris, France, 13–17 October, pp. 1–2 (2002)Google Scholar
  6. 6.
    Elias, P., Arthur, F., Gerhard, W.: Improvements of audio-based music similarity and genre classification. In: Processing of 6th International Conference on Music Information Retrieval, London, UK, 11–15 September, pp. 634–637 (2005)Google Scholar
  7. 7.
    Paul, Q., Robert, P., Michael, M., Maxwell, W., Scott, J., Richard, W.: Playlist generation, delivery and navigation. U.S. Patent No US20030135513 A1 (2002)Google Scholar
  8. 8.
    Shuo, C., Josh, L.M., Douglas T., Thorsten, J.: Playlist prediction via metric embedding. In: Processing of Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, USA, 12–16 August, pp. 714–722 (2012)Google Scholar
  9. 9.
    Gärtner, D.: User adaptive music similarity with an application to playlist generation. Ph.D. Thesis, University at Karlsruhe (TH), Germany, Carnegie Mellon University, Pittsburgh, PA, USA (2006)Google Scholar
  10. 10.
    Baltrunas, L., Kaminskas, M., Ludwig, B., Moling, O., Ricci, F., Aydin, A., Lüke, K.-H., Schwaiger, R.: InCarMusic: context-aware music recommendations in a car. In: Huemer, C., Setzer, T. (eds.) EC-Web 2011. LNBIP, vol. 85, pp. 89–100. Springer, Heidelberg (2011). doi: 10.1007/978-3-642-23014-1_8 CrossRefGoogle Scholar
  11. 11.
    Masahiro, N., Takaesu, H., Demachi, H., Oono, M., Saito, H.: Development of an automatic music selection system based on runner’s step frequency. In: Processing of 9th International Conference on Music Information Retrieval, Pennslyvania, USA, 14–18 September, pp. 193–198 (2008)Google Scholar
  12. 12.
    Wang, X., Wang, Y., Hsu, D., Wang, Y.: Exploration in interactive personalized music recommendation: a reinforcement learning approach. ACM Trans. Multimedia Comput. Commun. Appl. 11, 1–22 (2014)Google Scholar
  13. 13.
    Bogdanov, D., Herrera, P.: How much metadata do we need in music recommendation? A Subjective evaluation using preference sets. In: Processing of 12th International Conference on Music Information Retrieval, Miami, Florida, USA, 24–28 October, pp. 97–102 (2011)Google Scholar
  14. 14.
    Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. Adv. Neural Inf. Process. Syst. 26, 3111–3119 (2013)Google Scholar
  15. 15.
    Moore, J.L., Chen, S., Joachims, T., Turnbull, D.: Learning to embed songs and tags for playlists prediction. In: Processing of 13th International Society for Music Information Retrieval, Porto, Portugal, 8–12 October, pp. 349–354 (2012)Google Scholar
  16. 16.
    Shuo, C., Jiexun, X., Thorsten, J.: Multi-space probabilistic sequence modeling. In: Processing of the 19th ACM Conference on Knowledge Discovery and Data Mining, Chicago, USA, 11–14 August, pp. 865–873 (2013)Google Scholar
  17. 17.
    Bonnin, G., Jannach, D.: A comparison of playlist generation strategies for music recommendation and a new baseline scheme. In: Processing of the Twenty-Seventh AAAI Conference on Artificial Intelligence, Washington, USA, 16–18 July, pp. 16–23 (2013)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Computer Engineering DepartmentKocaeli UniversityIzmitTurkey

Personalised recommendations