Automatic Music Recommendation Based on Acoustic Content and Implicit Listening Feedback


  • Rodrigo Carvalho Borges Universidade de São Paulo, São Paulo, São Paulo, Brasil,
  • Marcelo Gomes de Queiroz Universidade de São Paulo, São Paulo, São Paulo, Brasil,



Music recommendation systems, Cold start, Collaborative filtering, Content-based recommendation, Codeword bernoulli average model, Vector quantization


Recommending music automatically isn’t simply about finding songs similar to what a user is accustomed to listen, but also about suggesting potentially interesting pieces that bear no obvious relationships to a user listen- ing history. This work addresses the problem known as “cold start”, where new songs with no user listening history are added to an existing dataset, and proposes a probabilistic model for inference of users listening interest on newly added songs based on acoustic content and implicit listening feedback. Experiments using a dataset of selected Bra- zilian popular music show that the proposed method compares favorably to alternative statistical models. 


Não há dados estatísticos.

Biografia do Autor

Rodrigo Carvalho Borges, Universidade de São Paulo, São Paulo, São Paulo, Brasil,

Marcelo Gomes de Queiroz, Universidade de São Paulo, São Paulo, São Paulo, Brasil,


DOMAVICIUS, Gediminas; TUZHILIN, Alexander. Toward the next generation of recommend- er systems: A survey of the state-of-the-art and possible extensions. IEEE Transactions on Knowl- edge and Data Engineering, 17(6):734–749, 2005.

BAEZA-YATES, Ricardo; RIBEIRO-NETO, Berthier; et al. Modern information retrieval, volume 463. ACM press New York., 1999.

CAMPOS, Luis M. de; LUNA, Juan M. Fernández; HUETE, Juan F.; MORALES, Miguel A. Rue- da. Combining content-based and collaborative recommendations: A hybrid approach based on bayesian networks. Int. J. Approx. Reasoning, 51(7):785–799, September 2010.

HERLOCKER, Jonathan L.; KONSTAN, Joseph A.; BORCHERS, Al; RIEDL, John. An algorith- mic framework for performing collaborative filtering. In: PROCEEDINGS OF THE 22ND AN- NUAL INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, SIGIR ’99, pages 230–237, New York, NY, USA, 1999.

HOFFMAN, Matthew D.; BLEI, David M.; COOK, Perry R.. Easy as CBA: A simple probabilistic model for tagging music. In: 10th INTERNATIONAL SOCIETY FOR MUSIC INFORMATION RETRIEVAL CONFERENCE. 2009.

HU, Yifan; KOREN, Yehuda; VOLINSKY, Chris. Collaborative filtering for implicit feedback da- tasets. In: ICDM’08. Eighth IEEE International Conference on Data Mining. p. 263-272, 2008.

LOGAN, Beth. Music recommendation from song sets. In: PROCEEDINGS OF THE ISMIR Con- ference, pages 425–428, 2004.

PARRA, Denis et al. Implicit feedback recommendation via implicit-to-explicit ordinal logistic regression mapping. In: PROCEEDINGS OF THE CARS, 2011.

ROLLING STONE BRAZIL. “Os 100 maiores discos da Música Brasileira” (The 100 greatest re- cords of Brazilian music) - Rolling Stone Brasil, october 2007, no. 13, page 109. Electronic Ver- sion [Online; accessed 28-December-2017]:

WANG, Xinxi; ROSENBLUM, David; WANG, Ye. Context-aware mobile music recommendation for daily activities. In: PROCEEDINGS OF THE 20th ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, p. 99-108, 2012.

XING, Zhe; WANG, Xinxi; WANG, Ye. Enhancing Collaborative Filtering Music Recommenda- tion by Balancing Exploration and Exploitation. In: PROCEEDINGS OF THE INTERNATION- AL SOCIETY FOR MUSIC INFORMATION RETRIEVAL (ISMIR), p. 445-450, 2014.

YOSHII, Kazuyoshi; GOTO, Masataka; KOMATANI, Kazunori; OGATA, Tetsuya; OKUNO, Hi- roshi G. An efficient hybrid music recommender system using an incrementally trainable prob- abilistic generative model. In: IEEE Transaction on Audio Speech and Language Processing, pag- es 435–447, 2008.



Como Citar

CARVALHO BORGES, R.; GOMES DE QUEIROZ, M. Automatic Music Recommendation Based on Acoustic Content and Implicit Listening Feedback. Música Hodie, Goiânia, v. 18, n. 1, p. 31–43, 2018. DOI: 10.5216/mh.v18i1.53569. Disponível em: Acesso em: 18 jul. 2024.