Skill-builder data 2009-2010
This is the 2009-10 data
The data is here: (Note: I, Neil Heffernan, get lots of requested that are asking
(It was hosted here.)
Update: Duplicated data records have been detected in the data sets that located at above links. A corrected version can be found here:
This file contains one row per student-problem (i.e. if student S answers problem P which has two skills, the two skills are collapsed into the format skill1_skill2 and represented in a single row):
https://drive.google.com/file/d/1NNXHFRxcArrU0ZJSb9BIL56vmUt5FhlE/view?usp=sharing
Skill builder problem sets have the following features:
Questions are based on one specific skill, a question can have multiple skill taggings.
Students must answer three questions correct in a row to complete the assignment;
If a student uses the tutoring ("Hint" or "Break this Problem Into Steps"), the question will be marked incorrect;
Students will know immediately if they answered the question correctly;
If a student is unable to figure out the problem on his or her own, the last hint will give the student the answer;
Currently, this feature is only available for math problem sets.
If you are using this data set please put into your publication this precise URL (https://sites.google.com/site/assistmentsdata/home/2009-2010-assistment-data/skill-builder-data-2009-2010 ) so others can know what data set you used.
If you are using it in a publication, please make reference to ASSISTments by citing our most commonly used paper to reference the ASSISTments system. (To be clear the paper below is from 2009 and does not use this data.)
Feng, M., Heffernan, N.T., & Koedinger, K.R. (2009). Addressing the assessment challenge in an Intelligent Tutoring System that tutors as it assesses. The Journal of User Modeling and User-Adapted Interaction, 19, 243-266. See more about this article here.
We think these papers used this data
Chris Piech, Jonathan Spencer, Jonathan Huang, Surya Ganguli, Mehran Sahami, Leonidas Guibas, & Jascha Sohl-Dickstein. (2015) Deep Knowledge Tracing. Retrieved from http://arxiv.org/pdf/1506.05908.pdf. I think it is going to NIPS. http://arxiv.org/abs/1506.05908
More info is available from this year school year here.
We recently in 2020 published a KDD paper with Andrew Lan and Ghosh at UMASS.
We are going to link this soon.
Dr Heffernan is aware of a some paper that have used this data set. He tries to keep track of such studies. He is aware of some work and he has a list here:
https://sites.google.com/site/assistmentsstudies/useourdata
If you know of a paper that uses this data set please send me a citation and link to the paper as I want to know and report to my funders.
June 2024: I am aware of one paper that tracks the 100+ papers that have used ASSISTments data.
Nasiar, N., Baker, R.S., Andres, J.M.A.L., Srivastava, N. (in press) Different AIED in Different Places: Tracing the differences in Geographical Distribution of Secondary Data Analysis and A/B tests. Proceedings of the 17th International Conference on Educational Data Mining. [pdf]
These two other papers might be of interest
Baker, R.S., Nasiar, N., Gong, W., Porter, C. (2022) The impacts of learning analytics and A/B testing research: a case study in diferential scientometrics. International Journal of STEM Education, 9, 6. [pdf]
Nasiar, N., Baker, R.S., Li, J., Gong, W. (2022) How do A/B Testing and secondary data analysis on AIED systems influence future research? Proceedings of the 23rd International Conference on Artificial Intelligence and Education, 115-126. [pdf]
We also have the 2014-2015 skill builder data set here.