Terms of use for ASSISTments data sets available at [ASSISTments website][1] We request that all papers using this data set cite one of the following three papers: (Use of rural, suburban, and urban data sets) Ocumpaugh, J., Baker, R., Gowda, S., Heffernan, N., Heffernan, C. (2014) Population validity for Educational Data Mining models: A case study in affect detection. British Journal of Educational Technology, 45 (3), 487-501. [pdf][2] [Use of suburban and urban data sets) Pardos, Z.A., Baker, R.S., San Pedro, M.O.C.Z., Gowda, S.M., Gowda, S.M. (2014) Affective states and state tests: Investigating how affect and engagement during the school year predict end of year learning outcomes. Journal of Learning Analytics, 1 (1), 107-128. [pdf][3] (Comparisons to deep learning model of student affect, for urban and suburban populations) Botelho, A.F., Baker, R., Heffernan, N. (2017) Improving Sensor-Free Affect Detection Using Deep Learning. Proceedings of the 18th International Conference on Artificial Intelligence in Education, 40-51. [pdf][4] [1]: https://docs.google.com/file/d/0B2X0QD6q79ZJd05rWl9kcWtoSjg/edit [2]: https://www.upenn.edu/learninganalytics/ryanbaker/BJET%20revised2%202013%20v30jlo%20%281%29.pdf [3]: https://www.upenn.edu/learninganalytics/ryanbaker/3536-15645-1-ED-v3.pdf [4]: https://www.upenn.edu/learninganalytics/ryanbaker/paper_59.pdf