Documentation
Open-access dataset for music education research by Yousician.
The dataset consists of the learning data of 1000 ukulele users (anonymised), covering the first 30 days after their signup to the Yousician app.
For every musical note or chord within every song that the users play, we include detailed information on what the user was supposed to play, whether the note or chord was played correctly, and how accurate was the timing. In the case of note pitch mistakes, we include information of which note was played instead, or if no note was played at all.
The dataset can be used, for example, to study what kind of mistakes learners make, what kind of learning difficulties they have, how their performance improves over time, and how different practising habits affect learning efficiently, to mention just a few.
Highlights
- Over 500K played song exercises, adding up to over 10M evaluated instances of notes, double stops, or chords
- Anonymised user ids and time data are provided, to explore approaches for personalised, adaptive instruction
- The learning path of each user can be ordered sequentially, to study/model instrumental learning, and forgetting, over time
- Over 100 different chord voicings
- Over 100 different double stop voicings
- Melodic (single note) instances covering roughly 2 octaves (C4-B5)
- Songs comprising a wide variety of styles, and difficulty levels