Music Artist Similarity Aggregation

  • Brandeis MarshallEmail author


Through user accounts, music recommendations are refined by user-supplied genres and artists preferences. Music recommendation is further complicated by multiple genre artists, artist collaborations and artist similarity identification. We focus primarily on artist similarity in which we propose a rank fusion solution. We aggregate the most similar artist ranking from Idiomag, and Echo Nest Web APIs. Each Web API and resulting ranked list using a rank fusion algorithm has a different method of relating their artists. Through an experimental evaluation of nearly 500 artist queries, we first identify a ground truth for artist similarity for comparison to five rank fusion algorithms and conduct a performance analysis to discern how well relevant information can be retrieved from biased multiple sources. By understanding this overlap, we can more easily isolate the multiple genre artists and artist collaborations.


Ground Truth Lower Precision Rank Position Music Genre Music Recommendation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Adalı, S., Hill, B., Magdon-Ismail, M.: Information vs. robustness in rank aggregation: Models, algorithms and a statistical framework for evaluation. Special Issue on Web Information Retrieval, J. Digit. Inform. Manage. 5(5), 292–307 (2007)Google Scholar
  2. 2.
    Bischoff, K., Firan, C., Nejdl, W., Paiu, T.: Can all tags be used for search. In: Proceedings of ACM CIKM, pp. 203–212 (2008)Google Scholar
  3. 3.
    Borda, J.C.: Mémoire sur les élections au scrutin. In Histoire de l’Académie Royale des Sciences (1781)Google Scholar
  4. 4.
    Brin, S., Page, L.: The anatomy of a large-scale hypertextual web search engine. In: Proceedings of ACM WWW, pp. 107–117 (1998)Google Scholar
  5. 5.
    Chen, H.-C., and Chen, A.L.P.: A music recommendation system based on music data grouping and user interests. In: Proceedings of ACM CIKM, pp. 231–238 (2001)Google Scholar
  6. 6.
    Chen, L., Wright, P., Nejdl, W.: Improving music genre classification using collaborative tagging data. In: Proceedings of the ACM International Conference on Web Search and Data Mining, pp. 84–93 (2009)Google Scholar
  7. 7.
    Cunningham, S., Bainbridge, D., McKay, D.: Finding new music: a diary study of everyday encounters with novel songs. In International Conference on Music Information Retrieval (ISMIR) pp. 83–88 (2007)Google Scholar
  8. 8.
    Dikerson, K.B., Ventura, D.: Music recommendation and query-by-content using self organizing maps. In: Proceedings of the International Joint Conference on Neural Networks pp. 705–710 (2009)Google Scholar
  9. 9.
    Dwork, C., Kumar, R., Naor, M., Sivakumar, D.: Rank aggregation methods for the web. In: Proceedings of ACM WWW pp. 613–622 (2001)Google Scholar
  10. 10.
    Ellis, D.P.W., Whitman, B., Berenzweig, A., Lawrence, S.: The quest for ground truth in musical artist similarity. In: Proceedings of the International Symposium on Music Information Retrieval pp. 170–177 (2002)Google Scholar
  11. 11.
    Fagin, R., Kumar, R., Sivakumar, D.: Efficient similarity search and classification via rank aggregation. In: Proceedings of ACM SIGMOD pp. 301–312 (2003)Google Scholar
  12. 12.
    Geleijnse, G., Schedl, M., Knees, P.: The quest for ground truth in musical artist tagging in the social web era. In: International Conference on Music Information Retrieval(ISMIR) pp. 525–530 (2007)Google Scholar
  13. 13.
    Im, I., Hars, A.: Does a one-size recommendation system fit all? the effectiveness of collaborative filtering based recommendation systems across different domains and search modes. ACM Trans. Inform. Syst. 26(1), (2007)Google Scholar
  14. 14.
    Knees, P., Pampalk, E., Widmer, G.: Artist classification with web-based data. In: Proceedings of the International Symposium on Music Information Retrieval pp. 517–524 (2004)Google Scholar
  15. 15.
    Lee, J.H.: Analyses of multiple evidence combination. In: Proceedings of ACM SIGIR pp. 267–276 (1997)Google Scholar
  16. 16.
    Magno, T., Sable, C.: A comparison of signal-based music recommendation to genre labels, collaborative filtering, musicological analysis, human recommendation, and random baseline. In: International Conference on Music Information Retrieval(ISMIR) pp. 161–166 (2008)Google Scholar
  17. 17.
    McKay, C., Fuhinaga, I.: Improving automatic music classification performance by extracting features from different types of data. In: Proceedings of the ACM SIGMM International Conference on Multimedia Information Retrieval pp. 257–266 (2010)Google Scholar
  18. 18.
    Montague, M., Aslam, J.A.: Condorcet fusion for improved retrieval. In: Proceedings of ACM CIKM pp. 538–548 (2002)Google Scholar
  19. 19.
    Shao, B., Li, T., Ogihara, M.: Quantity music artist similarity based on style and mood. In: Proceedings of the ACM International Workshop on Web Information and Data Management pp. 119–124 (2008)Google Scholar
  20. 20.
    Shen, J., Shepard, J., Cui, B., Tan, K.L.: A novel framework for efficient automated singer identification in large music databases. ACM Trans. Inform. Syst. 27(3), (2009)Google Scholar
  21. 21.
    Slaney, M., White, W.: Measuring playlist diversity for recommendation systems. In: Proceedings of the ACM Workshop on Audio and Music Computing Multimedia pp. 77–82 (2006)Google Scholar
  22. 22.
    Turnbull, D., Barrington, L., Lanckreit, G.: Five approaches to collecting tags for music. In: International Conference on Music Information Retrieval (ISMIR) pp. 225–230 (2008)Google Scholar

Copyright information

© Springer Vienna 2012

Authors and Affiliations

  1. 1.Computer and Information TechnologyPurdue UniversityWest LafayetteUSA

Personalised recommendations