This dataset is related to the paper:
Prihar, E., Patikorn, T., Botelho, A., Sales, A., & Heffernan, N. (2021, June). Toward Personalizing Students' Education with Crowdsourced Tutoring. In Proceedings of the Eighth ACM Conference on Learning at Scale (pp. 37-45).
This dataset contains 31,616 instances of a student requesting tutoring while completing a math problem in ASSISTments, receiving crowdsourced tutoring from one of 11 teachers, and then completing the problem they were struggling with and a problem afterward.
This data was used to fit models to determine which teachers' tutoring was most effective and to compare the tutoring of different teachers to each other.
To replicate the teacher comparisons done in the paper, place teacherassist_data.csv and analysis.ipynb in the same directory, then run all the cells in analysis.ipynb.