Name
Abstract | ||
|---|---|---|
In order to provide students with personalized practice recommendation in computer-aided intelligent education, a basic task is to predict students' performance in future exercises, in which it is essential to track the changes of knowledge acquired by each student in practice activities. But the existing methods can only use students' exercise records. Therefore, the rich information in the exercise is not fully utilized, so that it is impossible to achieve a more accurate prediction of student performance and a more explanatory analysis of knowledge acquisition. In this paper, we propose an overall study of student achievement prediction. In order to achieve the primary target of performance prediction, we use a variety of methods to fuse the exercise semantic information, and propose a deep knowledge tracking model that takes into account both knowledge concepts and exercise semantic information. In addition, in order to verify the portability of semantic extraction methods, we integrate semantic information into different deep knowledge tracing model. Through the experiment on the real online education data set, compared with the existing knowledge tracking model, the model proposed in this paper has better prediction performance. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1007/978-3-030-92836-0_24 | EMERGING TECHNOLOGIES FOR EDUCATION, SETE 2021 |
Keywords | DocType | Volume |
Deep learning, Knowledge tracking, Exercise semantic information | Conference | 13089 |
ISSN | Citations | PageRank |
0302-9743 | 0 | 0.34 |
References | Authors | |
0 | 6 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Rong Xiao | 1 | 0 | 0.34 |
| Ruili Zheng | 2 | 0 | 0.34 |
| Yongkang Xiao | 3 | 60 | 8.71 |
| Yinghui Zhang | 4 | 6 | 3.46 |
| Bo Sun | 5 | 104 | 21.35 |
| Jun He | 6 | 71 | 11.24 |