Freely Available Educational Data Sets
- LearnLab DataShop – registration is free but required, data sets can be analyzed online or downloaded for offline analysis
Sharing Your Own Data
- If you choose to make your data freely available, you can place it on your website, and email us to link it.
- Contact LearnLab to see if your data qualifies for inclusion into their DataShop.
- If you choose to share your data privately with colleagues, we have developed a standardized data sharing agreement which you can use, or adapt, when sharing data
Tools to Support Educational Data Mining
- Carnegie Mellon University’s PROJECT Listen has released the Bayes Net Toolkit for Student Modeling, a system which makes it easier to use Bayes Nets and Bayesian Knowledge-Tracing to model student data.
- LearnLab offers DataShop, a system which you can use to conduct learning curve analysis on educational data.
- Ryan Baker has made available tools for Bayesian Knowledge-Tracing (with brute force), distilling data features, for using models of gaming the system, off-task behavior, and guessing and slipping, and for statistically comparing A’ values.
- LearnSphere.org offers a web-based tool for authoring, sharing, and reusing analytic workflows and analytic components that can be recombined into new workflows.
Notes from Discussions at EDM Workshops
The EDM-ANNOUNCE and EDM-DISCUSS mailing lists are also maintained to support this research community.
If you have other resources which you would like us to add please email our website maintainer.