PCKT: Problem Composition in Knowledge Tracking
Open Access
- 28 October 2022
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 442-448
Abstract
With the rapid development of online education, personalized education becomes more and more important. The emergence of knowledge tracking (KT) has made a significant breakthrough in personalized education. In recent years, researchers have achieved some good results by building the KT model to search information and relationships between problems and skills. However, in reality, problems are sometimes similar. The skills may be exactly the same between two problems, but only the data is different. Therefore, it is extremely important to take this into account when making predictions. To address this problem, we construct a Problem Composition Knowledge Tracking Model (PCKT). In PCKT, problems are devided into corresponding data and skills, and connected by certain relation. Experiments demonstrated our PCKT achieved state-of-the-art results on two public datasets.Keywords
This publication has 7 references indexed in Scilit:
- Multi-Factors Aware Dual-Attentional Knowledge Tracing2021
- Temporal Cross-Effects in Knowledge Tracing2021
- Improving Knowledge Tracing via Pre-training Question Embeddings2020
- Dynamic Key-Value Memory Networks for Knowledge Tracing2017
- Towards better affect detectors2015
- Addressing the assessment challenge with an online system that tutors as it assessesUser Modeling and User-Adapted Interaction, 2009
- Knowledge tracing: Modeling the acquisition of procedural knowledgeUser Modeling and User-Adapted Interaction, 1995