All tools are copyright Ryan Baker and colleagues -- they are free for any
non-commercial or research use.
Partial credit for this distribution also accrues to Michael Sao Pedro, Ken Koedinger, Albert Corbett, Sujith Gowda, Aatish Salvi, Martin van Velsen, and Aaron Whiting, depending on tool. (Thanks for bug reports also goes out to Jim Kan and Robson Quel). Please contact me before using for
any commercial use. This code is NOT supported. Use it at your own risk, and make
sure to check that data is sorted properly.
You are welcome to re-distribute this code as long
as proper credit is given. If you use this code for a published paper, please
cite the appropriate paper listed below.
MOOC Replication Framework (MORF)
HART (Human Affect Recording Tool) [Source code] [Former dev site] (please cite Baker, Gowda, Wixon, Kalka, Wagner, Salvi, Aleven, Kusbit, Ocumpaugh, & Rossi, 2012) -- also see BROMP webpage
Bayesian Knowledge Tracing Brute Force model fitting code (please cite Baker, Corbett, Gowda, Wagner, MacLaren, Kauffman, Mitchell, & Giguere, 2010)
DataShop Feature Distillation (please cite Baker, Corbett, Koedinger, & Roll, 2008)
Gaming Detector (please cite Baker & de Carvalho, 2008) and Off-Task Behavior Detector (please cite Baker, 2007)
Models of Guessing and Slipping (please cite Baker, Corbett, & Aleven, 2008)
A'/AUC Code: GUI and code for computing A'/AUC that does not fail for cases where multiple data points have same
confidence; also can compare A'/AUC across models without violating independence assumption (please cite Baker,
Corbett, & Aleven, 2008) (version 5, February 2018) (version 4.1, command-line, November 2020)
Also see the Penn Center for Learning Analytics Github page