Skip to content

Latest commit

 

History

History
97 lines (69 loc) · 4.92 KB

README.md

File metadata and controls

97 lines (69 loc) · 4.92 KB

ISMIR 2020 - International Society for Music Information Retrieval GitHub repo size

Detecting Collaboration Profiles in Success-based Music Genre Networks

Abstract

We analyze and identify collaboration profiles in success-based music genre networks. Such networks are built upon data recently collected from both global and regional Spotify weekly charts. Overall, our findings reveal an increase in the number of distinct successful genres from high-potential markets, pointing out that local repertoire is more important than ever on building the global music ecosystem. We also detect collaboration patterns mapped into four different profiles: Solid, Regular, Bridge and Emerging, wherein the two first depict higher average success. These findings indicate great opportunities for the music industry by revealing the driving power of inter-genre collaborations within regional and global markets.

Goals and Contributions

We believe factors leading to an ideal musical partnership can be understood by exploring collaboration patterns that directly impact its success. Hence, we aim to unveil the dynamics of cross-genre connections and collaboration profiles in success-based networks (i.e., connections formed by genres of artists who cooperate and create hit songs). We do so through the following research questions (RQ).

  • RQ1 Does the regional aspect impact on popular genres and their hit songs?

  • RQ2 How has genre collaboration evolved over the past few years?

  • RQ3 Which are the potentially intrinsic factors and indicators that influence the collaboration success?

In order to answer such questions, we first model genre collaboration in the music scenario as success-based networks. Then, we build a novel dataset with data from global and regional markets and present the network science concepts and metrics required for understanding the paper. Overall, our analyses and experiments over the networks reveal that:

  1. Individually analyzing regional markets is fundamental, as local genres play a key role on determining hit songs and popular artists.
  2. In general, genre collaborations are increasing, with emerging local genres hitting global success -- despite the differences in the evolution of regional markets.
  3. Genre collaborations analyses describe three significant factors (Attractiveness, Affinity and Influence), to uncover four profiles (Solid, Regular, Bridge and Emerging).

MGD - Music Genre Dataset

  1. Genre Networks: Success-based genre collaboration networks. (612 KB)
  2. Genre Mapping: Genre mapping from Spotify genres to super-genres. (6 KB)
  3. Artist Networks: Success-based artist collaboration networks. (423 KB)
  4. Artists: Some artist data. (473 KB)
  5. Hit Songs: Hit Song data and features. (1.4 MB)
  6. Charts: Enhanced data from Spotify Weekly Top 200 Charts. (13.6 MB)

Statistics


Data # Records
Songs 13,880
Artists 3,612
Genres 896

The Team

  • 👨 Gabriel P. Oliveira page
  • 👩 Mariana O. Silva page
  • 👨 Danilo B. Seufitelli page
  • 👨 Anisio Lacerda page
  • 👩 Mirella M. Moro page

Source (citation)

@inproceedings{ismir/OliveiraSSLM20,
  title = {Detecting Collaboration Profiles in Success-based Music Genre Networks},
  author = {Gabriel P. Oliveira and 
            Mariana O. Silva and 
            Danilo B. Seufitelli and 
            Anisio Lacerda and
            Mirella M. Moro},
  booktitle = {21st International Society for Music Information Retrieval Conference}
  pages = {726--732},
  year = {2020}
}

License

  • The dataset is meant for research purposes.

Acknowledgments

This work is supported by CAPES, CNPq and FAPEMIG, Brazil.