Deep Knowledge Tracing with Learning Curves

Yang, Shanghui; Liu, Xin; Su, Hang; Zhu, Mengxia; Lu, Xuesong

doi:10.1109/icdmw58026.2022.00046

Cited by 2 publications

(2 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the DKT model representing the mastery of students over KC with hidden states, it cannot provide detailed output regarding students' mastery levels for each KC. Yang S. et al (2020) combine the forgetting curve theory, which posits that human memory declines over time, and propose the CKT model. This model uses LSTM to capture long-term features and leverages 3D Conv to enhance the short-term effects of recent exercises, effectively modeling the forgetting curve in students' learning processes.…”

Section: Knowledge Tracing Models Based On DLmentioning

confidence: 99%

GTFN

Huang,

Wei

2024

International Journal of Data Warehousing and Mining

View full text Add to dashboard Cite

With the development of smart education, gaining insights into students' understanding during the learning process is crucial in teaching. However, traditional knowledge tracking methods face challenges in capturing the intricate relationships between problems and knowledge points, as well as students' temporal learning changes. Therefore, we design a knowledge tracking model based on a graph temporal fusion network. Firstly, we construct the structure of the question and knowledge skill graph. Then, we design a knowledge graph encoder layer to capture the complex relationships between questions and knowledge skills. Next, we apply a sequential information extraction layer to dynamically model the outputs of each layer in the upper network over time, capturing students' knowledge changes at different time steps. Finally, we use a dynamic attention aggregation network to learn node information at different levels and time sequences. Experimental results on three datasets demonstrate the effectiveness of our method.

show abstract

Section: Knowledge Tracing Models Based On DLmentioning

confidence: 99%

GTFN

Huang,

Wei

2024

International Journal of Data Warehousing and Mining

View full text Add to dashboard Cite

show abstract

“…First, we describe the CAKT model (Yang et al, 2022 ) that adopts a 3D-ConvNets module to model the learning curve, i.e., capturing the feature from past trials on the same knowledge concept. Figure 2A illustrates the architecture of CAKT, which consists of the 3D-ConvNets module (top) and the two-layer LSTM network (bottom).…”

Section: The Cakt Modelmentioning

confidence: 99%

Deep knowledge tracing with learning curves

Liu

Yang

et al. 2023

Front. Psychol.

Self Cite

View full text Add to dashboard Cite

Knowledge tracing (KT) models students' mastery level of knowledge concepts based on their responses to the questions in the past and predicts the probability that they correctly answer subsequent questions in the future. Recent KT models are mostly developed with deep neural networks and have demonstrated superior performance over traditional approaches. However, they ignore the explicit modeling of the learning curve theory, which generally says that more practices on the same knowledge concept enhance one's mastery level of the concept. Based on this theory, we propose a Convolution-Augmented Knowledge Tracing (CAKT) model and a Capsule-Enhanced CAKT (CECAKT) model to enable learning curve modeling. In particular, when predicting a student's response to the next question associated with a specific knowledge concept, CAKT uses a module built with three-dimensional convolutional neural networks to learn the student's recent experience on that concept, and CECAKT improves CAKT by replacing the global average pooling layer with capsule networks to prevent information loss. Moreover, the two models employ LSTM networks to learn the overall knowledge state, which is fused with the feature learned by the convolutional/capsule module. As such, the two models can learn the student's overall knowledge state as well as the knowledge state of the concept in the next question. Experimental results on four real-life datasets show that CAKT and CECAKT both achieve better performance compared to existing deep KT models.

show abstract

Deep Knowledge Tracing with Learning Curves

Cited by 2 publications

References 36 publications

GTFN

GTFN

Deep knowledge tracing with learning curves

Contact Info

Product

Resources

About