Martín, D., Frantz, B. and Pachet, F. Improving music composition through peer feedback: experiment and preliminary results. Workshop AI and Feedback, 24th International Joint Conference on Artificial Intelligence (IJCAI 2015), Buenos Aires, Argentina, July 2015

Sony CSL authors: Daniel Martin Martinez, François Pachet

Abstract

To which extent peer feedback can affect the quality of a music composition? How does musical experience influence the quality of a feedback during the song composition process? To answer these questions we designed and conducted an experiment in which participants compose short songs using an online lead sheet editor, are given the possibility to feedback on other participant’s songs and can either accept or reject feedback on their compositions. This experiment aims at collecting quantitative data relating the intrinsic quality of songs (estimated by peer evaluation) with the nature of feedback. Preliminary results show that peer feedback can indeed improve both the quality of a song composition and the composer’ satisfaction about it. Also, composers tend to prefer compositions from other musicians with similar musical experience level.

Keywords: feedback, creativity

Downloads

[PDF] Adobe Acrobat PDF file

BibTeX entry

@INPROCEEDINGS { dani:15b, ADDRESS="Buenos Aires, Argentina", AUTHOR="Martín, D. and Frantz, B. and Pachet, F.", BOOKTITLE="Workshop AI and Feedback, 24th International Joint Conference on Artificial Intelligence (IJCAI 2015)", MONTH="July", TITLE="Improving music composition through peer feedback: experiment and preliminary results", YEAR="2015", }