Alternative Methods for Deriving Emotion Metrics in the Spotify® Recommendation Algorithm
Spotify's® recommendation algorithm tailors music offerings to create a unique listening experience for each user. Though what this recommender does is highly impressive, there is always room for improvement given that these techniques are not fully prescient. This study posits that in addition to creating certain features based on audio analysis, incorporating new features derived from album art color as well as lyrical sentiment analysis may provide additional value to the end user. This team did not find that a significant difference existed between color valence and Spotify® valence; however, all other comparisons resulted in statistically significant difference of means using paired t-tests. Due to the failure in finding a significant difference between color valence and Spotify® valence, this team is of the opinion that if a relationship between the two is found after additional exploration, they could be used in conjunction with one another to recommend music more accurately to listeners. Alternatively, there may be value in the statistical difference of the other variables, whereby further research may demonstrate a purpose in leveraging the differences.
Sherga, Ronald M. Jr.; Wei, David; Benson, Neil; and Javed, Faizan
"Alternative Methods for Deriving Emotion Metrics in the Spotify® Recommendation Algorithm,"
SMU Data Science Review: Vol. 5:
3, Article 3.
Available at: https://scholar.smu.edu/datasciencereview/vol5/iss3/3
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial 4.0 License