BILLBOARD HIT SONG PREDICTION BASED ON AUDIO AND TEXT FEATURES

Authors

  • Sandra Rajanović Autor

DOI:

https://doi.org/10.24867/13BE18Rajanovic

Keywords:

machine learning, hit song prediction, natural language processing

Abstract

This paper presents creating a system for Billboard hit song prediction using their audio features and lyrics. The binary classification problem solution was implemented using multiple machine learning models and two natural language processing methods, all created in Python programming language.

References

[1] Y. Ni, R. Santos-Rodriguez, M. Mcvicar and T. De Bie, "Hit song science once again a science", 4th International Workshop on Machine Learning and Music, 2011.
[2] J. Devlin, M.W. Chang, K. Lee and K. Toutanova, "Bert: Pre-training of deep bidirectional transformers for language understanding", arXiv preprint arXiv:1810.04805, 2018.
[3] https://www.billboard.com/charts/hot-100
[4] https://www.spotify.com/
[5] https://genius.com/
[6] K. Middlebrook and K. Sheik, "Song Hit Prediction: Predicting Billboard Hits Using Spotify Data", arXiv preprint arXiv:1908.08609, 2019.
[7] E. Georgieva, M. Suta and N. Burton, "HITPREDICT: PREDICTING HIT SONGS USING SPOTIFY DATA", 2018.
[8] A. Singhi and D.G. Brown, "Can song lyrics predict hits", Proceedings of the 11th International Symposium on Computer Music Multidisciplinary Research, pp. 457-471, 2015.
[9] R. Dhanaraj and B. Logan, "Automatic Prediction of Hit Songs", ISMIR, pp. 488-491, 2005.

Published

2021-07-03

Issue

Section

Electrotechnical and Computer Engineering