Applying machine learning to identify musical taste

Authors

DOI:

https://doi.org/10.5335/rbca.v11i3.9230

Keywords:

Machine learning, support vector machine, k-nearest neighbor

Abstract

Discovering the musical taste of a person have an obvious application in recommendation mechanisms used
by online music service providers. We are interested in a less obvious application, which is related to the
work environment of a software developer. In this particular work we compare two algorithms used in data
mining as classifiers. The goal is to compare Support Vector Machine (SVM) and k-Nearest Neighbor (k-NN)
as predictors of the musical taste of a user. To run the experiment we used a database of songs that have
been previously classified with a label indicating whether the user likes or dislikes each song. The database
includes a set of features of the songs, each classifier uses the same combinations of features in the learning
process and then classify new instances of songs according to the user’s predicted taste. This initial study
indicated that SVM is a better predictor than k-NN for this particular context. In future investigations we
intend to evaluate the user in an synchronous environment, our hypothesis is that it might be possible to
understand more than the like / dislike scenario and expand to what the user wants to hear at a particular
moment, with that we plan to capture the current mood of the user. Eventually we want to correlate the
mood of a software developer to the fault proneness of the code she has written

Downloads

Download data is not yet available.

Published

2019-09-13

Issue

Section

Original Paper

How to Cite

[1]
2019. Applying machine learning to identify musical taste. Brazilian Journal of Applied Computing. 11, 3 (Sep. 2019), 88–98. DOI:https://doi.org/10.5335/rbca.v11i3.9230.