• P-ISSN 0974-6846 E-ISSN 0974-5645

Indian Journal of Science and Technology

Article

Predicting Music Popularity Using Spotify and YouTube Features
  • VIEWS 1747
  • PDF 905

Indian Journal of Science and Technology

DOI: 10.17485/IJST/v15i36.2332

Year: 2022, Volume: 15, Issue: 36, Pages: 1786-1799

Original Article

Predicting Music Popularity Using Spotify and YouTube Features

Yap Kah Yee1*, Mafas Raheem1

1School of Computing, Asia Pacific University of Technology & Innovation, Kuala Lumpur, Malaysia

*Correponding Author
Email: [email protected]

 

Received Date:13 December 2022, Accepted Date:23 August 2022, Published Date:21 September 2022

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstract

Objectives: To examine whether the integration of Social Media features from YouTube videos and Spotify audio features can effectively predict music popularity. Methods: A dataset is constructed by collecting newly released tracks from May to August 2021. Audio features are acquired from Spotify while social media features are obtained from the official videos on YouTube. Music popularity is defined using five metrics derived from the Spotify Top 200 daily chart performance to measure diverse aspects of the songs’ success (Length, Max, Sum, Mean, and Debut). The predicted popularity has three target variables, ranging from Low, Medium to High popularity. During model implementation, four machine learning models were trained on the dataset in two different stages such as purely audio features and both audio and social media features respectively. Findings: At the second stage, random forest outperformed the other three models with the best results for the four-evaluation metrics. In detail, the model generated accuracy of 79.6%, macro-precision of 74.5%, macro-recall of 73.2%, and macro F1-scores of 73.1% on average across the five-popularity metrics used. Moreover, the results from both experimental stages showed that the incorporation of social media variables significantly increased the model performances relative to the use of audio features only, with the margins of improvement ranging from 10% to 60%. This demonstrates that YouTube-based social media features are beneficial for the use of industry practitioners to identify potentially popular hits. Novelty: This research appears to be the first study to date in the Hit Song Science domain that utilizes Social Media data from YouTube for the prediction of hit songs. Furthermore, it promotes the prediction of potential hits by using audio features and social media data jointly.

Keywords: hit song science; machine learning; audio features; social media features; Spotify; YouTube

References

  3. Ahmad IS, Bakar AA, Yaakub MR. Movie Revenue Prediction Based on Purchase Intention Mining Using YouTube Trailer Reviews. Information Processing & Management. 2020;57(5):102278. Available from: https://doi.org/10.1016/j.ipm.2020.102278
  4. Watts D, Hasker S. Marketing in an unpredictable world. Available from: https://hbr.org/2006/09/marketing-in-an-unpredictable-world (accessed )
  5. Interiano M, Kazemi K, Wang L, Yang J, Yu Z, Komarova NL. Musical trends and predictability of success in contemporary songs in and out of the top charts. Royal Society Open Science. 2018;5(5):171274. Available from: https://royalsocietypublishing.org/doi/10.1098/rsos.171274
  6. Kim ST, Oh JH. Music intelligence: Granular data and prediction of top ten hit songs. Decision Support Systems. 2021;145:113535. Available from: https://doi.org/10.1016/j.dss.2021.113535
  7. Middlebrook K, Sheik K. Song hit prediction: Predicting billboard hits using Spotify data. Available from: https://arxiv.org/pdf/1908.08609 (accessed )
  8. Zangerlee, Vötter M, Huber R, Yang YH. Hit Song Prediction: Leveraging Low-and High-Level Audio Features. In: Proceedings of the 20th ISMIR Conference. (pp. 319-326) 2019.
  9. Martin-Gutierrez D, Penaloza GH, Belmonte-Hernandez A, Garcia FA. A Multimodal End-to-End Deep Learning Architecture for Music Popularity Prediction. IEEE Access. 2020;8:39361–39374. Available from: https://doi.org/10.1109/ACCESS.2020.2976033
  10. Singhi A, Brown DG. Can song lyrics predict hits. Proceedings of the 11th International Symposium on Computer Music Multidisciplinary Research. 2015. P. 457-471. . Available from: https://cs.uwaterloo.ca/~browndg/CMMR15data/CMMR2015paper.pdf
  11. Herremans D, Bergmans T. Hit song prediction based on early adopter data and audio features. Available from: https://arxiv.org/pdf/2010.09489 (accessed )
  13. Kim ST, Oh JH. Music intelligence: Granular data and prediction of top ten hit songs. Decision Support Systems. 2021;145:113535. Available from: https://doi.org/10.1016/j.dss.2021.113535.
  14. Middlebrook K, Sheik K. Song hit prediction: Predicting billboard hits using spotify data. Available from: https://arxiv.org/pdf/1908.08609 (accessed )
  15. Lee J, Lee JS. Music Popularity: Metrics, Characteristics, and Audio-Based Prediction. IEEE Transactions on Multimedia. 2018;20(11):3173–3182. Available from: https://doi.org/10.1109/TMM.2018.2820903
  16. Araujo CS, Cristo M, Giusti R. Predicting Music Popularity on Streaming Platforms. Anais do Simpósio Brasileiro de Computação Musical (SBCM 2019). 2020;27:108–117.
  19. Liikkanen LA, Salovaara A. Music on YouTube: User engagement with traditional, user-appropriated and derivative videos. Computers in Human Behavior. 2015;50:108–124. Available from: https://doi.org/10.1016/j.chb.2015.01.067
  20. Breiman L. Random forests. Machine Learning. 2001;45:5–32. Available from: https://doi.org/10.1023/A:1010933404324
  21. Biau G, Scornet E. A random forest guided tour. TEST. 2016;25(2):197–227. Available from: https://doi.org/10.1007/s11749-016-0481-7
  22. Opitz J, Burst S. Macro F1 and macro F1. Available from: https://arxiv.org/pdf/1911.03347.pdf (accessed )
  24. Raza AH, Nanath K. Predicting a Hit Song with Machine Learning: Is there an apriori secret formula? 2020 International Conference on Data Science, Artificial Intelligence, and Business Analytics (DATABIA). 2020;p. 111–116. Available from: https://doi.org/10.1109/DATABIA50434.2020.9190613
  25. Oh C, Roumani Y, Nwankpa JK, Hu HFF. Beyond likes and tweets: Consumer engagement behavior and movie box office in social media. Information & Management. 2017;54(1):25–37. Available from: https://doi.org/10.1016/j.im.2016.03.004
  26. Ouyang S, Li C, Li X. A Peek Into the Future: Predicting the Popularity of Online Videos. IEEE Access. 2016;4:3026–3033. Available from: https://doi.org/10.1109/ACCESS.2016.2580911

Copyright

© 2022 Yee & Raheem. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Published By Indian Society for Education and Environment (iSee) 

  • 21 September 2022

Year: 2022, Volume: 15, Issue: 36

Article Metrics


Post Graduate Fellowship in Research Communication

More articles

DON'T MISS OUT!

Subscribe now for latest articles and news.