This is a webpage for the paper The Sequence of Action Model: Leveraging the Sequence of Attempts and Hints, published in the proceedings of the 2014 Educational Data Mining BKT20y Workshop by Linglong Zhu, Yutao Wang and Neil T. Heffernan.
In this paper, we build a Sequence of Actions (SOA) model taking advantage of the sequence of hints and attempts a student needed for previous question to predict students’ performance. Students who make attempts have higher next correct percentage than students who ask for hints. A two-step modeling methodology is put forward in the work, which is a combination of Tabling method and the Logistic Regression. The experimental results showed that the Sequence of Action model has reliably better predictive accuracy than KT and AM and its performance of prediction is improved after combining with KT.
Introductions of files attached to this website:
InputData: you need it for all experiments.
Each of the other .rar files includes input data, matlab code and experiment results for each experiment.
Linglong Thesis: this file is the thesis work of Linglong Zhu, which has more details about the model and experiments.