EarSketch CAI

Engaging high school students in computer science with co-creative learning companions (Funding: National Science Foundation, DRL-1813740)


Computer science is becoming a ubiquitously needed skill in the 21st century, and we have seen the emergence of innovative approaches for K-12 that are rapidly gaining adoption. The EarSketch learning environment engages learners in programming by allowing them to control musical samples, beats, and effects with computer code in Python or JavaScript. The Cai (Co-creative AI) project scaffolds deep computer science learning within an environment that fosters creative expression. This project is led by PI Brian Magerko and co-PI Jason Freeman at the Georgia Institute of Technology and by PI Kristy Boyer at the University of Florida.

Project Description

The Cai project leverages state-of-the-art research in co-creative artificial intelligence (AI) and intelligent pedagogical support, along with well-informed studies of human collaboration and the widely-adopted EarSketch CS learning platform. We will build the first-of-its-kind co-creative learning companion, powered by artificial intelligence. EarSketch's co-creative learning companion will not act as an authority figure, but rather as a peer. Cai will collaborate with learners to make music and code as a partner, sometimes leading by example to introduce important computer science constructs, while often supporting or deferring to the student's creative choices. We will iteratively refine Cai to be particularly effective within the context of high school computer science classrooms, in close partnership with teachers and diverse students through participatory design. We will engage a broad audience of high school learners by building on the success of EarSketch for empowering underrepresented populations in computing and creating on-demand, personalized support that scaffolds the learning process.


[7]A Validation Study of an Automated, Formative Assessment of Creativity in a Computational Music Remixing Learning Environment. Seyedahmad Rahimi, Jason B. Smith, Erin Truesdell, Ashvala Vinay, Kristy Elizabeth Boyer, Brian Magerko, Tom McKlin. Division:10 Society for the Psychology of Aesthetics, Creativity, and the Arts (PACA), Symposium: Machines Learn to Judge Creativity: AI Advances in Automated Assessment, Denton, Texas, 2024, pp. To appear. [bib]
[6]Exploring Usability Issues in Instruction-Based and Schema-Based Authoring of Task-Oriented Dialogue Agents. Amogh Mannekote, Mehmet Celepkolu, Joseph B. Wiggins, Kristy Elizabeth Boyer. Proceedings of the 5th International Conference on Conversational User Interfaces, 2023, pp. 1-6. [bib] [doi]
[5]The Relationship between Co-Creative Dialogue and High School Learners' Satisfaction with their Collaborator in Computational Music Remixing. Gloria Ashiya Katuka, Alexander Webber, Joseph B. Wiggins, Kristy Elizabeth Boyer, Brian Magerko, Tom McKlin, Jason Freeman. Proceedings of the ACM on Human-Computer Interaction, vol. 6 no. CSCW1, 2022, pp. 1-24. [bib] [doi]
[4]Investigating the Relationship Between Dialogue States and Partner Satisfaction During Co-Creative Learning Tasks. Amanda E. Griffith, Gloria Ashiya Katuka, Joseph B. Wiggins, Kristy Elizabeth Boyer, Jason Freeman, Brian Magerko, Tom McKlin. International Journal of Artificial Intelligence in Education, 2022. [bib] [doi]
[3]Modeling Music and Code Knowledge to Support a Co-creative AI Agent in Education. Jason Smith, Erin Truesdell, Jason Freeman, Brian Magerko, Kristy Elizabeth Boyer, Tom McKlin. In Proceedings of the 21st International Society for Music Information Retrieval Conference (ISMIR 2020), 2021, pp. 131-141. [bib]
[2]Supporting Computational Music Remixing with a Co-Creative Learning Companion. Erin Truesdell, Jason Smith, Sarah Mathew, Tom McKlin, Gloria Ashiya Katuka, Amanda E. Griffith, Brian Magerko, Jason Freeman, Kristy Elizabeth Boyer. Proceedings of the 12th International Conference on Computational Creativity, 2021, pp. 113-121. [bib]
[1]Discovering Co-creative Dialogue States during Collaborative Learning. Amanda E. Griffith, Gloria Ashiya Katuka, Joseph B. Wiggins, Kristy Elizabeth Boyer, Jason Freeman, Brian Magerko, Tom McKlin. Proceedings of the International Conference on Artificial Intelligence in Education, 2021, pp. 165-177. [bib] [doi]