Deep Knowledge Tracking based on Attention Mechanism for Student Performance Prediction

Liu, Dong; Dai, Huanhuan; Zhang, Yunping; Li, Qinpeng; Zhang, Congpin

doi:10.1109/csei50228.2020.9142472

Cited by 6 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper compares our model with DKT [4], SAKT [9], and MAKT [11], which have been described in the previous introductory sections. DKT uses a single-layer recurrent neural network for student performance prediction and is a ground-breaking approach in the field of deep knowledge tracing.…”

Section: Methodsmentioning

confidence: 99%

“…Traditional KT is based on Bayes theorem, and it uses a Hidden Markov model to represent the student's knowledge state as a hidden variable. Hidden Markov model do not perform well on long sequence problems because they assume that the present topic is just relationally connected to the previous status [9]. Based on BKT, [10] proposed richer extensions by considering individual students.…”

Section: Knowledge Tracingmentioning

confidence: 99%

See 1 more Smart Citation

A deep knowledge tracing model based on multi-head self-attention mechanism

Zhou,

Wu,

Huang

et al. 2023

International Conference on Algorithms, High Performance Computing, and Artificial Intelligence (AHPCAI 2023)

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 99%

Section: Knowledge Tracingmentioning

confidence: 99%

A deep knowledge tracing model based on multi-head self-attention mechanism

Zhou,

Wu,

Huang

et al. 2023

International Conference on Algorithms, High Performance Computing, and Artificial Intelligence (AHPCAI 2023)

View full text Add to dashboard Cite

“…In order to solve these problems, many researchers are committed to in-depth research on DKT and put forward many new methods. Dong et al [7] used Jaccard coefficient to calculate the attention weight between knowledge components in the model a-dkt, and combined LSTM and total attention value to get the final prediction result. Zhang et al [8] used the method of feature engineering to add the dimension reduction of answer time, answer times and the first action to the input layer of LSTM by using an auto-encoder.…”

Section: Related Workmentioning

confidence: 99%

Using Multi-feature Embedding towards Accurate Knowledge Tracing

Yu¹,

Chen²,

Huang³

et al. 2022

Proceedings of the 34th International Conference on Software Engineering and Knowledge Engineering

View full text Add to dashboard Cite

Knowledge tracing is a crucial task in intelligent tutoring systems. Aiming at the shortcomings of traditional knowledge tracing technology such as low prediction accuracy, overfitting and low utilization of multi-features, this paper proposes a knowledge tracing model SRGCA-M using multi-feature embedding with stacked residual GRU network. Compared with the traditional methods that only use the historical record of answering exercises, our approach utilizes a variety of features in the learning process of students to deep characterize students' learning. We increase the layers number of GRU network to expand the capacity of sequence learning and use residual connections to solve the problems of network degradation and vanishing gradient. We use the auto-encoder to solve the problem that the cross-feature encoding will rapidly increase the dimension of the input data. Comprehensive experimental results demonstrate that compared with various advanced techniques, our approach can not only achieve better performance of tracking knowledge changes of students but also fully utilize multi-feature information of students in the learning process.

show abstract