Accesso libero

Construction of personalized online educational resources based on deep learning in higher education self-study examination environment

Anxue Zhao

Anxue Zhao

School of Information Science and Technology, Qiongtai Normal UniversityHaikou, China
Cerca questo autore su
Sciendo|Google Scholar
Zhao, Anxue
 e 
Xiaoting Jia

Xiaoting Jia

School of Information Science and Technology, Qiongtai Normal UniversityHaikou, China
Cerca questo autore su
Sciendo|Google Scholar
Jia, Xiaoting
  
19 mar 2025
Construction of personalized online educational resources based on deep learning in higher education self-study examination environment's Cover Image
INFORMAZIONI SU QUESTO ARTICOLO
Articolo precedente
Articolo Successivo
Cita
Scarica la copertina
Pubblicato online: 19 mar 2025
Ricevuto: 06 nov 2024
Accettato: 14 feb 2025
DOI: https://doi.org/10.2478/amns-2025-0550
Parole chiave
© 2025 Anxue Zhao et al., published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

Personalized test recommendation method based on GFLDKT model
Personalized test recommendation method based on GFLDKT model

Figure 2.

System architecture of the online education resources cloud platform
System architecture of the online education resources cloud platform

Figure 3.

Model training loss curve
Model training loss curve

Figure 4.

Information status changes visualization
Information status changes visualization

Figure 5.

Information status changes visualization
Information status changes visualization

Figure 6.

Question analysis
Question analysis

Figure 7.

Changes in the 1 value of the assitments2015 data set
Changes in the 1 value of the assitments2015 data set

Figure 8.

Changes in the 1 value of the statics2011 data set
Changes in the 1 value of the statics2011 data set

Average level of knowledge changes

[λ1, λ2] 0.1-0.3 0.3-0.5 0.5-0.7 0.7-0.9 0.9-1.0
ASSITments2015 ΔB 0.0172 0.0192 0.0263 0.0168 0.0162
Statics2011 ΔB 0.0114 0.0138 0.0196 0.0093 0.0091

Experimental results and model performance contrast

ASSIST2009 ASSIST2015 ASSIST chall
ACC AUC ACC AUC ACC AUC
Model 0.562 0.6 0.551 0.567 0.507 0.51
BKT 0.677 0.712 0.671 0.679 0.67 0.685
DKT 0.657 0.666 0.656 0.66 0.653 0.668
DKVMN 0.699 0.737 0.692 0.732 0.672 0.693
GIKT 0.705 0.723 0.714 0.753 0.688 0.727
EERNN 0.71 0.737 0.727 0.765 0.7 0.762
LPKT 0.738 0.781 0.724 0.764 0.721 0.752
ATKT 0.734 0.773 0.726 0.757 0.719 0.758
This model 0.823 0.827 0.824 0.816 0.818 0.821

Compare the probability of the correct answer in the data set

[λ1, λ2] 0-0.2 0.2-0.4 0.4-0.6 0.6-0.8 0.8-1.0
ASSITments2015 SR 0.938 0.749 0.586 0.389 0.164
Statics2011 SR 0.925 0.682 0.495 0.327 0.229

The contrast effect in the statics2011 data set

PMF UserCF This Model
precision 0.807 0.815 0.829
recall 0.24 0.248 0.253
f1 0.395 0.404 0.407

The contrast effect in the assistments2015 data set

PMF UserCF This Model
precision 0.862 0.888 0.923
recall 0.195 0.209 0.213
f1 0.354 0.374 0.397
Lingua:
Inglese
Frequenza di pubblicazione:
1 volte all'anno
Argomenti della rivista:
Scienze biologiche, Scienze della vita, altro, Matematica, Matematica applicata, Matematica generale, Fisica, Fisica, altro
Feed RSS della rivista