Name
Abstract | ||
|---|---|---|
We present text replays, a method for generating labels that can be used to train classifiers of student behavior. We use this method to label data as to whether students are gaming the system, within 20 intelligent tutor units on Algebra. Text replays are 2-6 times faster per label than previous methods for generating labels, such as quantitative field observations and screen replays; however, being able to generate classifiers on retrospective data at the coder's convenience (rather than being dependent on visits to schools) makes this method about 40 times faster than quantitative field observations. Text replays also give precise predictions of student behavior at multiple grain-sizes, allowing the use of both hierarchical classifiers such as Latent Response Models (LRMs), and non-hierarchical classifiers such as Decision Trees. Training using text replay data appears to lead to better classifiers: LRMs trained using text replay data achieve higher correlation and A' than LRMs trained using quantitative field observations; Decision Trees are more precise than LRMs at identifying exactly when the behavior occurs. However, developing classifiers of student behavior has thus far been either highly time- consuming or has resulted in classifiers that are difficult to validate. In this paper, we present a method for quickly and accurately labeling data in terms of student behavior - text replays. The entire process of creating a detector for a unit in an intelligent tutor is about 40 times faster when text replays are used, compared to prior data labeling methods such as quantitative field observations or screen replays. Text replays also produce data which can be more easily used with off-the-shelf classification algorithms, such as those in Weka (21), than field observations. We validate this method by using it to develop classifiers of gaming the system for 20 different Cognitive Tutor lessons on algebra, and study those detectors' ability to predict which students game, how much they game, and when they game. |
Year | Venue | Keywords |
|---|---|---|
2008 | EDM | grain size,decision tree |
Field | DocType | Citations |
Decision tree,TUTOR,Computer science,Artificial intelligence,Machine learning | Conference | 27 |
PageRank | References | Authors |
1.61 | 11 | 2 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ryan S. J. d. Baker | 1 | 1220 | 111.60 |
| Adriana M. J. B. de Carvalho | 2 | 67 | 5.81 |