Continuous Student Knowledge Tracing Using SVD and Concept Maps

Teodorescu, Oana Maria; Popescu, Paul Ștefan; Mocanu, L. M.; Mihăescu, Marian Cristian

doi:10.4316/aece.2021.01008

Cited by 2 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…F KS = {GLU(Conv 1d(F ILA ))} 3 (7) where F LIS is the embedded matrix expression of the learning interaction sequence U k .…”

Section: Using Cnn To Extract Spatial Features Of Students' Learning ...mentioning

confidence: 99%

“…LMSs have rich resources, flexibility, and convenience, which brings new development opportunities for intelligent education [6]. As a crucial research branch of intelligent education, knowledge tracing (KT), which promotes solving the problem of personalized tutoring for learners, has attracted more and more attention [7]. KT can model and analyze the data of interactions from learners practicing online to obtain the potential law of the change of different students' knowledge status, and then predict students' future learning performance [8].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Knowledge Tracing Based on Spatial and Temporal Representation Learning for Learning Performance Prediction

et al. 2022

View full text Add to dashboard Cite

Knowledge tracing (KT) serves as a primary part of intelligent education systems. Most current KTs either rely on expert judgments or only exploit a single network structure, which affects the full expression of learning features. To adequately mine features of students’ learning process, Deep Knowledge Tracing Based on Spatial and Temporal Deep Representation Learning for Learning Performance Prediction (DKT-STDRL) is proposed in this paper. DKT-STDRL extracts spatial features from students’ learning history sequence, and then further extracts temporal features to extract deeper hidden information. Specifically, firstly, the DKT-STDRL model uses CNN to extract the spatial feature information of students’ exercise sequences. Then, the spatial features are connected with the original students’ exercise features as joint learning features. Then, the joint features are input into the BiLSTM part. Finally, the BiLSTM part extracts the temporal features from the joint learning features to obtain the prediction information of whether the students answer correctly at the next time step. Experiments on the public education datasets ASSISTment2009, ASSISTment2015, Synthetic-5, ASSISTchall, and Statics2011 prove that DKT-STDRL can achieve better prediction effects than DKT and CKT.

show abstract

“…F KS = {GLU(Conv 1d(F ILA ))} 3 (7) where F LIS is the embedded matrix expression of the learning interaction sequence U k .…”

Section: Using Cnn To Extract Spatial Features Of Students' Learning ...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep Knowledge Tracing Based on Spatial and Temporal Representation Learning for Learning Performance Prediction

et al. 2022

View full text Add to dashboard Cite

show abstract

“…LMSs have rich resources, flexibility, and convenience, which brings new development opportunities for intelligent education [6,7]. As a crucial research branch of intelligent education, knowledge tracing (KT), which promotes solving the problem of personalized tutoring for learners, has attracted more and more attention [8]. KT can model and analyze the data of interactions from learners practicing online to obtain the potential law of the change of different students' knowledge status, and then predict students' future learning performance [9].…”

Section: Introductionmentioning

confidence: 99%