Date of Award

Summer 8-2018

Document Type

Thesis

Degree Name

Master of Music (MM)

Department

Music

First Advisor

Alejandro Cremaschi

Second Advisor

Andrew Cooperstock

Third Advisor

Alexandra Nguyen

Abstract

Modern music tutoring software and mobile instructional applications have great potential to help students practice at home effectively. They can offer extensive feedback on what the student is getting right and wrong and have adopted a gamified design with levels, badges, and other game-like elements to help gain wider appeal among students. Despite their advantages for motivating students and creating a safe practice environment, no current music instruction software demonstrates any knowledge about a student’s level of mastery. This can lead to awkward pedagogy and user frustration. Applying Bayesian Knowledge Tracing to tutoring systems provides an ideal way to track and predict student knowledge and skills. This thesis explains how to utilize Bayesian Knowledge Tracing in music practice software and discusses the benefits over existing pedagogical software

Share

COinS