Validity and Fairness of an Automated Assessment of Creativity in Computational Music Remixing

Creativity is one of the most crucial skills for success in life in the 21st century. However, assessing creativity in an automated, objective way is challenging. In this study, we designed and validated an automated assessment (an unobtrusive, formative assessment) of creativity in EarSketch, a computational music remixing platform where students write Python or JavaScript code to create pieces of music. Specifically, using an existing dataset of EarSketch projects (n = 53), we investigated the validity and fairness of an automated assessment of creativity. Our findings show that the automated assessment of creativity has reasonable convergent validity (r = .50) and discriminant validity; and this assessment is fair (i.e., no significant differences in terms of gender, grade, or race were found). The results of this research have the potential to inform the design of innovative educational programs and interventions that foster creativity and innovation in STEM education. As we continue to explore new ways of assessing creativity, we can pave the way for a more creative and innovative society, where individuals are equipped with the skills they need to tackle future challenges.