| Description |
The dataset used in the challenge comes from a study of novice Python
programmers working with the ITAP intelligent tutoring system. For
more information on the original experiment, see . There are 89 total
students represented, and they worked on 38 problems over time. The
study lasted over 7 weeks. The students could attempt the problems in
any order, though there was a default order. Students could attempt the
problem any number of times, receiving feedback from test cases each
time, and they could also request hints from ITAP (though access was
limited for students, depending on the week and their experimental
condition). The dataset itself contains a record for each attempt and
hint request that students made while working. |
| Related Publication |
@inproceedings{10.1145/2960310.2960333,
author = {Rivers, Kelly and Harpstead, Erik and Koedinger, Ken},
title = {Learning Curve Analysis for Programming: Which Concepts do Students Struggle With?},
year = {2016},
isbn = {9781450344494},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/2960310.2960333},
doi = {10.1145/2960310.2960333},
abstract = {The recent surge in interest in using educational data mining on student written programs has led to discoveries about which compiler errors students encounter while they are learning how to program. However, less attention has been paid to the actual code that students produce. In this paper, we investigate programming data by using learning curve analysis to determine which programming elements students struggle with the most when learning in Python. Our analysis extends the traditional use of learning curve analysis to include less structured data, and also reveals new possibilities for when to teach students new programming concepts. One particular discovery is that while we find evidence of student learning in some cases (for example, in function definitions and comparisons), there are other programming elements which do not demonstrate typical learning. In those cases, we discuss how further changes to the model could affect both demonstrated learning and our understanding of the different concepts that students learn.},
booktitle = {Proceedings of the 2016 ACM Conference on International Computing Education Research},
pages = {143–151},
numpages = {9},
keywords = {educational data mining, knowledge components, learning curve analysis, programming syntax},
location = {Melbourne, VIC, Australia},
series = {ICER '16}
} |